© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48331
    Prev
    Next
    INDEX
    Explanations

    log every keystroke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ها
    0.49
    ,
    0.45
     ,
    0.45
    ं
    0.45
    >
    0.44
    /
    0.43
    Albert
    0.42
    採用
    0.42
    vai
    0.41
    &
    0.41
    POSITIVE LOGITS
     Joystick
    0.50
     Freighter
    0.47
     रीजनिंग
    0.45
     সেইরূপ
    0.45
     डिजाईन
    0.45
    ત્રો
    0.45
    ifizieren
    0.45
     لئے
    0.44
     Madness
    0.44
     Gorge
    0.44
    Activations Density 0.001%

    No Known Activations