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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67844
    Prev
    Next
    INDEX
    Explanations

    common words and phrases

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

    The neuron fires on the core technical content words in a question—key nouns and verbs (e.g. “string,” “search,” “address,” “domain,” “prop”) that name what the user wants to act on.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     økonom
    -0.86
    ো
    -0.82
     user
    -0.82
     adjacent
    -0.81
     after
    -0.79
     during
    -0.79
     financieras
    -0.79
     diarias
    -0.78
    pgf
    -0.77
    uco
    -0.77
    POSITIVE LOGITS
     they
    1.71
     shared
    1.58
     them
    1.55
    让他们
    1.48
    共通
    1.43
     common
    1.39
    给他们
    1.38
    COMMON
    1.34
    shared
    1.33
     ihnen
    1.32
    Activations Density 0.145%

    No Known Activations