© 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. 17645
    Prev
    Next
    INDEX
    Explanations

    future

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

    future concepts

    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
    、
    0.74
    ،
    0.70
    การณ์
    0.60
    ü
    0.60
    ，
    0.59
    ช่วง
    0.59
    予測
    0.57
     unfl
    0.57
    ين
    0.56
    ת
    0.56
    POSITIVE LOGITS
    u
    0.70
     (
    0.70
    на
    0.68
    k
    0.67
    rana
    0.64
    ang
    0.62
    the
    0.61
    lar
    0.61
    kuk
    0.61
    kob
    0.60
    Activations Density 0.037%

    No Known Activations