© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71197
    Prev
    Next
    INDEX
    Explanations

    programming keywords like var, const, unsigned

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

    The neuron responds to numeric literal tokens in code.

    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
     kullan
    -1.13
    خخ
    -1.12
    badan
    -1.09
    karakter
    -1.09
     warszawa
    -1.05
     toate
    -1.05
    <%@
    -1.03
    jawab
    -1.03
    ofern
    -1.02
    Answered
    -1.02
    POSITIVE LOGITS
     each
    1.12
     jeweiligen
    0.95
    intele
    0.93
     каждого
    0.93
    [
    0.92
    cerea
    0.91
    }(
    0.91
    ->
    0.87
     بعدی
    0.87
     [
    0.86
    Activations Density 0.008%

    No Known Activations