© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107227
    Prev
    Next
    INDEX
    Explanations

    everyday and ordinary phrases

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

    The neuron detects ordinary or clichéd descriptive phrases—common idiomatic adjectives like “everyday,” “ho-hum,” “run-of-the-mill,” “cookie-cutter,” and “common-sense.”

    oai_token-act-pair · o4-miniTriggered 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
    /");
    -0.77
     petits
    -0.75
     grievance
    -0.73
     Trento
    -0.73
    freopen
    -0.72
     darbu
    -0.71
     مد
    -0.69
    郷
    -0.69
     toimi
    -0.69
    //**
    -0.69
    POSITIVE LOGITS
     everyday
    2.06
    everyday
    1.76
     Everyday
    1.75
    Everyday
    1.75
    aday
    1.43
    day
    1.22
     day
    1.21
     cotidiana
    1.11
    Day
    1.07
     codzien
    1.07
    Activations Density 0.015%

    No Known Activations