© 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. 16154
    Prev
    Next
    INDEX
    Explanations

    date, time, or list separators

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

    FOR IMMEDIATE RELEASE

    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
     آور
    0.45
    杳
    0.43
    ሞች
    0.42
     الجزء
    0.42
     ارو
    0.41
    étend
    0.40
     اہمیت
    0.39
    されています
    0.39
    arkar
    0.39
     Agama
    0.39
    POSITIVE LOGITS
     groups
    0.50
    嚯
    0.45
    പ്പ
    0.42
    फ्त
    0.41
     groupings
    0.41
    캔
    0.41
    <h1>
    0.41
     banks
    0.40
    ৎস
    0.40
     caches
    0.39
    Activations Density 0.001%

    No Known Activations