© 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. 75862
    Prev
    Next
    INDEX
    Explanations

    `Elect` `/*` `The` `Chat` `1`

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

    The neuron is keyed to sequences of leading or repeated whitespace (indentation) in code or markup.

    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
    árias
    -0.77
     coronel
    -0.72
     Luther
    -0.71
     uncovered
    -0.68
     พิ
    -0.68
     prenda
    -0.67
     prosper
    -0.66
    ավ
    -0.65
    中には
    -0.65
     maestra
    -0.65
    POSITIVE LOGITS
     sở
    0.77
    क्षा
    0.77
     Keeper
    0.75
     độ
    0.74
     collaborator
    0.74
    ¾
    0.74
    StateList
    0.73
     Freestyle
    0.72
     Collegiate
    0.71
    getLatitude
    0.70
    Activations Density 0.009%

    No Known Activations