© 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. 47434
    Prev
    Next
    INDEX
    Explanations

    code definitions and parameters

    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
    Muted
    -0.76
     hazards
    -0.75
    Lengths
    -0.71
    lastTime
    -0.71
    nodeId
    -0.70
     Dust
    -0.69
    前は
    -0.69
    euse
    -0.68
    Mocks
    -0.66
     Mafia
    -0.66
    POSITIVE LOGITS
    archivo
    0.79
    اش
    0.75
     relatifs
    0.73
     дея
    0.72
    Références
    0.72
     privately
    0.71
     list
    0.71
    seler
    0.71
     private
    0.70
    ся
    0.70
    Activations Density 0.037%

    No Known Activations