© 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. 18032
    Prev
    Next
    INDEX
    Explanations

    range, season, hours, weather

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

    long backend bootstrap

    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
    LEMENT
    0.53
     চলমান
    0.50
    협
    0.49
    ArrayIndex
    0.45
    σεις
    0.45
     ইসলামী
    0.44
    个数
    0.44
     благоприят
    0.43
     rectMode
    0.43
    ACTIONS
    0.43
    POSITIVE LOGITS
     quatre
    0.52
     six
    0.48
     nine
    0.46
     three
    0.46
    ش
    0.46
     redes
    0.46
     Pré
    0.45
     agus
    0.43
    یده
    0.43
     Mais
    0.43
    Activations Density 0.000%

    No Known Activations