© 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. 57614
    Prev
    Next
    INDEX
    Explanations

    SQL CREATE TABLE statements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     configureStore
    -0.84
     Probably
    -0.81
    pokem
    -0.79
     some
    -0.78
    lint
    -0.77
     fabric
    -0.75
     unparalleled
    -0.74
     Presbyterian
    -0.72
     that
    -0.71
     Though
    -0.71
    POSITIVE LOGITS
    charAt
    0.97
    DELIM
    0.97
    ˂
    0.95
    dao
    0.94
    ajax
    0.92
     dao
    0.91
    servlet
    0.91
     QUÉ
    0.91
    Interceptor
    0.89
    Filesystem
    0.89
    Activations Density 0.001%

    No Known Activations