© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65099
    Prev
    Next
    INDEX
    Explanations

    double-blind, year, path, licensed

    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
     Bắc
    -0.71
    Gentile
    -0.71
    リヤ
    -0.71
     RARE
    -0.70
     backed
    -0.70
     fou
    -0.69
     변
    -0.69
    MOH
    -0.68
    取り付け
    -0.67
    ANNOUNC
    -0.67
    POSITIVE LOGITS
     SRS
    0.72
    ąpi
    0.70
    של
    0.70
    ارج
    0.70
    Ya
    0.69
    rice
    0.69
    Although
    0.67
    弓
    0.67
    Two
    0.67
     clinch
    0.67
    Activations Density 0.061%

    No Known Activations