© 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. 34-GEMMASCOPE-RES-131K
    7. 93592
    Prev
    Next
    INDEX
    Explanations

    HTML tags or identifiers

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

    This neuron strongly responds to programming identifiers and JSON field names (e.g. snake_case or CamelCase tokens like “created_at,” “full_name,” “Release,” “DownloadCount,” etc.).

    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
    uncu
    -0.76
    geist
    -0.75
     lvl
    -0.75
    componentWill
    -0.74
     fér
    -0.74
    ivoli
    -0.74
     kaikk
    -0.73
     Ivan
    -0.73
    mouseX
    -0.73
     feared
    -0.72
    POSITIVE LOGITS
    Html
    1.14
     Html
    0.91
     html
    0.90
    nodeId
    0.89
    html
    0.89
    setLogin
    0.88
    NodeId
    0.85
    setUrl
    0.85
    SPC
    0.85
     HTML
    0.82
    Activations Density 0.014%

    No Known Activations