© 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. 101540
    Prev
    Next
    INDEX
    Explanations

    Caribbean islands and places

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

    outline, assumes, privacy

    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
     обучение
    0.47
     вскоре
    0.47
     вдоль
    0.47
    诈
    0.45
     кров
    0.45
    >→</
    0.45
     ब्लॉग
    0.44
     괜찮
    0.44
    .")]
    0.44
     हात
    0.43
    POSITIVE LOGITS
    PREFIX
    0.49
     Namen
    0.44
    Aff
    0.44
    MAJOR
    0.44
    Vancouver
    0.42
    ثم
    0.42
    Therm
    0.42
    t
    0.42
    ST
    0.42
    multiple
    0.42
    Activations Density 0.005%

    No Known Activations