© 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. 111864
    Prev
    Next
    INDEX
    Explanations

    direction or state

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

    API Endpoints

    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
    0
    0.53
    <0xEB>
    0.52
    treated
    0.51
     year
    0.48
    resize
    0.47
    subdir
    0.47
    valence
    0.46
    iculos
    0.46
    s
    0.46
    )$;
    0.46
    POSITIVE LOGITS
    啼
    0.48
    IVATE
    0.47
    нути
    0.47
     ULT
    0.46
    路
    0.46
     ROAD
    0.46
     راستہ
    0.46
    佈
    0.43
     равна
    0.43
     RAIL
    0.42
    Activations Density 0.000%

    No Known Activations