© 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. 34-GEMMASCOPE-RES-131K
    7. 59427
    Prev
    Next
    INDEX
    Explanations

    documentation files

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

    The neuron fires on technical/documentation and file‐format keywords—things like “documentation,” “json,” “password_token,” “format,” 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
     Emerson
    -0.75
     motorcycle
    -0.74
    removeItem
    -0.73
    ToAction
    -0.73
    getColor
    -0.70
    Feng
    -0.70
     drop
    -0.69
    chev
    -0.69
     $-
    -0.69
    🐦
    -0.68
    POSITIVE LOGITS
    Majority
    0.71
     Majority
    0.69
    ALLEN
    0.66
    abito
    0.65
     majority
    0.65
     Foreword
    0.64
     maj
    0.63
    Tray
    0.61
     Inhalt
    0.61
    粮食
    0.60
    Activations Density 0.071%

    No Known Activations