© 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. 34-GEMMASCOPE-RES-131K
    7. 98297
    Prev
    Next
    INDEX
    Explanations

    code symbols and comments

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

    The neuron fires on programming‐language keywords, symbols, and identifiers (e.g. “if”, “Input”, “::”, comment markers, code variable names), i.e. code syntax elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Faire
    -0.81
     httpClient
    -0.77
    lanze
    -0.76
    緊
    -0.72
     Geol
    -0.71
    enschappelijke
    -0.70
     axles
    -0.69
     piste
    -0.68
    ཨ
    -0.68
    物質
    -0.67
    POSITIVE LOGITS
     Input
    2.38
    Input
    2.11
     Request
    1.64
     request
    1.37
    Request
    1.30
    request
    1.29
     input
    1.15
     Inputs
    1.06
    input
    1.02
     INPUT
    0.96
    Activations Density 0.038%

    No Known Activations