© 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. 60850
    Prev
    Next
    INDEX
    Explanations

    lists like cruelty-free

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

    most ornery

    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
    ライブ
    0.56
    وري
    0.54
    ﺮ
    0.49
    IK
    0.47
    能力
    0.46
    オス
    0.46
    Wiring
    0.45
    2
    0.45
    ُر
    0.45
    しい
    0.45
    POSITIVE LOGITS
    endige
    0.53
    尷
    0.47
    foration
    0.47
    pointee
    0.46
    elina
    0.46
     mocker
    0.45
     ताब
    0.44
     firmness
    0.44
     Bulg
    0.44
     πίνα
    0.43
    Activations Density 0.000%

    No Known Activations