© 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. 182589
    Prev
    Next
    INDEX
    Explanations

    presented shows

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

    on and behalf of

    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
    ופ
    0.52
    MovieModal
    0.46
     articles
    0.45
     옵
    0.45
     المواد
    0.45
    וע
    0.44
    뭣
    0.44
    fieldContext
    0.44
    HttpContext
    0.44
    벼
    0.44
    POSITIVE LOGITS
    строен
    0.48
     regina
    0.48
    om
    0.48
    al
    0.46
    。『
    0.46
     decir
    0.46
    उन
    0.45
    イヤ
    0.45
    nown
    0.45
     surpr
    0.44
    Activations Density 0.000%

    No Known Activations