© 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. 175511
    Prev
    Next
    INDEX
    Explanations

    dance movements

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

    location information and responsibility

    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
    బ్ర
    0.45
     `<=
    0.45
    INCRE
    0.45
    กรม
    0.44
    ಫ
    0.44
    崔
    0.43
     솔
    0.43
    書法
    0.42
    ヘ
    0.42
    킁
    0.42
    POSITIVE LOGITS
     satın
    0.48
     Union
    0.45
    ông
    0.44
    am
    0.43
    Union
    0.43
    unku
    0.43
     zakup
    0.42
     zahval
    0.42
    Village
    0.42
     vistazo
    0.42
    Activations Density 0.000%

    No Known Activations