© 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. 64182
    Prev
    Next
    INDEX
    Explanations

    seeking advice or information

    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
    薔薇
    -0.77
    ッカー
    -0.73
    ázs
    -0.70
    avenir
    -0.69
    реги
    -0.69
     saliv
    -0.69
     avenir
    -0.69
    ῇ
    -0.68
     Sys
    -0.68
    OOTDTY
    -0.68
    POSITIVE LOGITS
     turn
    4.69
    turn
    4.13
     turned
    4.00
     turning
    3.98
    Turn
    3.86
    Turning
    3.67
     turns
    3.53
    turning
    3.53
     Turn
    3.50
     Turning
    3.50
    Activations Density 0.079%

    No Known Activations