© 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. 130388
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on programming‐style delimiters and terminators (e.g. braces, semicolons, parentheses, and similar punctuation).

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

    code and structure elements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     also
    -1.40
    ifah
    -1.05
    тию
    -1.02
     those
    -0.98
     but
    -0.96
    discussed
    -0.95
     koti
    -0.94
    have
    -0.94
    stri
    -0.93
    also
    -0.93
    POSITIVE LOGITS
     altijd
    1.14
     Grecia
    1.05
     arque
    1.05
    ﷺ
    1.02
    [
    1.02
    ztes
    0.99
     Arque
    0.98
     ends
    0.96
    槃
    0.95
     наконец
    0.95
    Activations Density 0.016%

    No Known Activations