© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6851
    Prev
    Next
    INDEX
    Explanations

    code or file paths with errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     won
    0.71
    ksh
    0.64
     فهر
    0.63
     पंकज
    0.61
    canic
    0.61
    தை
    0.61
    ාවේ
    0.61
    ={{
    0.60
    βα
    0.60
     regularmente
    0.60
    POSITIVE LOGITS
     Conjecture
    0.59
     Societies
    0.57
    य़
    0.53
    летия
    0.53
    拆
    0.52
    愎
    0.51
     Trigger
    0.51
    预防
    0.50
     Eliminate
    0.50
     Extrem
    0.50
    Activations Density 0.009%

    No Known Activations