© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77899
    Prev
    Next
    INDEX
    Explanations

    not the usual or typical

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on idiomatic “your … ” clichés—especially the phrase “your run-of-the-mill” (and similar “your average” constructions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    idiomatic “your + generic descriptor” constructions that denote something as typical or average, often in contrasts that negate typicality.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases describing something as ordinary, commonplace, or typical (often in the context "not your typical/average/run of the mill").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arithmic
    -0.90
     sätt
    -0.89
    anthin
    -0.85
     někter
    -0.82
    cobs
    -0.81
    малар
    -0.78
    шено
    -0.77
     Ges
    -0.77
     flecha
    -0.77
    織
    -0.77
    POSITIVE LOGITS
     typical
    4.06
     average
    3.94
    average
    3.34
    typical
    3.30
    Typical
    3.08
    Average
    2.84
     ordinary
    2.81
     Typical
    2.78
     Average
    2.55
     типи
    2.55
    Activations Density 0.037%

    No Known Activations