© 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. 86713
    Prev
    Next
    INDEX
    Explanations

    assignee shall succeed

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

    mathematical explanations and code

    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
     πίνακα
    0.53
    vať
    0.50
     انف
    0.49
    ونکو
    0.49
     сом
    0.48
     انس
    0.48
     בנו
    0.47
     ב
    0.47
     зво
    0.47
     ე
    0.47
    POSITIVE LOGITS
    imed
    0.55
    il
    0.54
    ineries
    0.53
    chloride
    0.48
     sanitary
    0.48
    Kon
    0.47
    iss
    0.46
    २
    0.45
    の方が
    0.44
    Kami
    0.43
    Activations Density 0.001%

    No Known Activations