© 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. 10-GEMMASCOPE-RES-131K
    7. 112391
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

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

    the word "template" in programming and configuration contexts.

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

    The neuron fires on occurrences of the word “template.”

    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
    s
    -2.28
     \&
    -1.98
     \{
    -1.82
     rychle
    -1.75
     lascia
    -1.74
     trovano
    -1.74
    läufig
    -1.73
     Garantía
    -1.71
    みよう
    -1.71
    都在
    -1.71
    POSITIVE LOGITS
     that
    2.23
    .”
    2.23
     unquestionably
    1.96
    i
    1.92
    ,”
    1.85
    ي
    1.81
    at
    1.77
    a
    1.74
    ⭓
    1.73
    ୮
    1.73
    Activations Density 0.020%

    No Known Activations