© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6759
    Prev
    Next
    INDEX
    Explanations

    describing states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    фера
    0.51
     жё
    0.50
    푅
    0.47
    忔
    0.47
     처
    0.46
    ologien
    0.45
    쏜
    0.45
     meget
    0.43
    fetched
    0.43
    ;|
    0.43
    POSITIVE LOGITS
     drama
    0.47
    າວ
    0.45
     dialysis
    0.44
    de
    0.44
     komunitas
    0.43
    די
    0.43
    veg
    0.42
    א
    0.42
    ald
    0.42
    linux
    0.42
    Activations Density 0.000%

    No Known Activations