© 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. 192028
    Prev
    Next
    INDEX
    Explanations

    decisions and dates

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

    code, settings, characters

    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
     entier
    0.50
    rón
    0.50
     與
    0.49
     Lords
    0.48
     Abb
    0.48
     เงี้ย
    0.48
    遏
    0.47
    百年
    0.46
     israel
    0.45
     Ridg
    0.45
    POSITIVE LOGITS
    так
    0.52
    0.47
    CELL
    0.47
    Õ
    0.45
    SETTINGS
    0.44
    Some
    0.44
    WELL
    0.44
    TS
    0.43
    EST
    0.43
    WHAT
    0.42
    Activations Density 0.001%

    No Known Activations