© 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. 206363
    Prev
    Next
    INDEX
    Explanations

    black velvet

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

    size and memory reduction

    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
     Eighth
    0.49
     Purple
    0.48
     请
    0.47
     PlayStation
    0.46
     Britann
    0.46
     Johannesburg
    0.46
     ಗೆ
    0.45
     Flyers
    0.45
     Wallpaper
    0.45
     Pottery
    0.45
    POSITIVE LOGITS
    которы
    0.52
    ck
    0.52
    jes
    0.52
    ok
    0.50
    eit
    0.49
    eln
    0.49
    ກ
    0.48
    d
    0.48
    ak
    0.48
    cmake
    0.47
    Activations Density 0.001%

    No Known Activations