© 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. 157338
    Prev
    Next
    INDEX
    Explanations

    damage caused by

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

    shared or predictable

    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
     রাস্তায়
    0.54
     Asimismo
    0.52
     kunci
    0.50
    <unused2126>
    0.50
     unfounded
    0.48
     लंबी
    0.47
     conquistar
    0.47
     छोटी
    0.47
     quitter
    0.47
     шесть
    0.47
    POSITIVE LOGITS
    وا
    0.59
    ه
    0.50
    ب
    0.49
    Standards
    0.49
    мі
    0.49
    fass
    0.49
    纯
    0.48
    Matrix
    0.48
    نا
    0.47
    终端
    0.47
    Activations Density 0.001%

    No Known Activations