© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    singlehandedly, divine intervention, major, interesting, PaaS

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

    creating branches and curriculum

    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
     drilled
    0.44
    orted
    0.43
    大量
    0.42
    '
    0.41
    对待
    0.40
    接受
    0.40
     branded
    0.40
    hre
    0.40
    elling
    0.39
    丢失
    0.39
    POSITIVE LOGITS
    ʘ
    0.50
    °;
    0.48
     ءِ
    0.48
     لینا
    0.46
     Summon
    0.45
    ColorLegend
    0.45
     앞으로
    0.45
     聞い
    0.44
     অতঃ
    0.44
     เอา
    0.43
    Activations Density 0.000%

    No Known Activations