© 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. 65859
    Prev
    Next
    INDEX
    Explanations

    PCT patent applications

    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
    ARCH
    -0.83
    addToCart
    -0.75
     Fal
    -0.72
     ※
    -0.72
    [-
    -0.71
    Arch
    -0.71
     Shooting
    -0.69
     Soo
    -0.69
    consul
    -0.69
    lius
    -0.68
    POSITIVE LOGITS
    gewiesen
    0.76
    될
    0.75
     distritos
    0.72
    üsü
    0.72
    loro
    0.71
    莒
    0.69
     골
    0.69
    トラック
    0.68
    uelan
    0.67
     서비스
    0.66
    Activations Density 0.045%

    No Known Activations