© 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. 99557
    Prev
    Next
    INDEX
    Explanations

    background information

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

    background context

    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
    ка
    0.73
    います
    0.71
    ö
    0.67
     кораб
    0.66
    <0xA6>
    0.65
     измерения
    0.64
     домой
    0.64
    下來
    0.64
     have
    0.63
    arı
    0.62
    POSITIVE LOGITS
     Background
    1.28
     background
    1.24
    background
    1.19
     배경
    1.19
    Background
    1.14
     backgrounds
    1.11
    i
    1.05
    ে
    1.03
     Hintergrund
    0.97
     BACKGROUND
    0.96
    Activations Density 0.015%

    No Known Activations