© 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. 173543
    Prev
    Next
    INDEX
    Explanations

    specializes in theory

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

    server handles, moisture creates

    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
     ПК
    0.57
    verz
    0.52
    іб
    0.51
     dropper
    0.51
     використа
    0.49
     використання
    0.49
    栊
    0.48
    秾
    0.48
     छत
    0.46
    ੀ
    0.46
    POSITIVE LOGITS
     Incorporated
    0.48
    last
    0.48
     Sex
    0.46
     Im
    0.46
     specializes
    0.46
     Last
    0.45
     Shed
    0.45
     Endocrinology
    0.45
     Cardiovascular
    0.45
     Avant
    0.45
    Activations Density 0.001%

    No Known Activations