© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105436
    Prev
    Next
    INDEX
    Explanations

    test descriptions and iterators

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

    variable or parameter references in programming code, particularly the token "it" and variable names used in expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron responds to the token “it.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     our
    -1.83
    comuna
    -1.81
    袛
    -1.79
     использованием
    -1.78
    ﹅
    -1.73
    焢
    -1.65
     obiet
    -1.61
    鷓
    -1.61
    Válasz
    -1.59
    髫
    -1.59
    POSITIVE LOGITS
     It
    2.05
    {
    1.77
    </strong>
    1.77
     {
    1.73
     are
    1.72
     cuando
    1.72
    ?
    1.72
     ``
    1.63
     quando
    1.54
    到来
    1.53
    Activations Density 0.001%

    No Known Activations