© 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. 60035
    Prev
    Next
    INDEX
    Explanations

    data types and column definitions

    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
    SCRIPT
    -0.86
    jukan
    -0.82
     Bricks
    -0.81
    Bricks
    -0.79
    iseta
    -0.79
     PSS
    -0.79
    Fotos
    -0.78
     potongan
    -0.77
     Rockstar
    -0.77
     Gilles
    -0.77
    POSITIVE LOGITS
     drill
    0.90
     enabled
    0.77
    drill
    0.77
     drilling
    0.76
     Alberta
    0.75
    RTEX
    0.74
     بو
    0.71
    ccoli
    0.71
     me
    0.69
     kap
    0.69
    Activations Density 0.001%

    No Known Activations