© 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. 57273
    Prev
    Next
    INDEX
    Explanations

    State, County, Court, University

    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
    広報
    -0.75
     feedback
    -0.73
     respir
    -0.71
     potenti
    -0.71
     Stal
    -0.69
    úrese
    -0.69
    wet
    -0.69
     +
    -0.68
    الة
    -0.67
     incomp
    -0.66
    POSITIVE LOGITS
    awić
    0.88
     Gaston
    0.84
     Boiling
    0.81
     inyección
    0.79
     &,
    0.77
    Raf
    0.74
    weebly
    0.74
    outez
    0.74
    ="#
    0.73
     sachsen
    0.72
    Activations Density 0.007%

    No Known Activations