© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 145738
    Prev
    Next
    INDEX
    Explanations

    products, brands, services

    np_acts-logits-general · gemini-2.5-flash-lite

    docker compose rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughter
    0.49
     worship
    0.45
    拄
    0.45
    inar
    0.44
    isam
    0.44
    mér
    0.44
    resión
    0.43
    愛情
    0.43
    幣
    0.43
     moistur
    0.43
    POSITIVE LOGITS
     regola
    0.46
    рез
    0.44
    ником
    0.44
    kd
    0.42
     Ecole
    0.42
     défis
    0.42
     reto
    0.41
     desafios
    0.41
    깐
    0.41
    NSInteger
    0.41
    Activations Density 0.001%

    No Known Activations