© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51815
    Prev
    Next
    INDEX
    Explanations

    index.html

    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_40_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
    <
    0.47
    excluding
    0.40
    Gen
    0.40
    Hus
    0.39
    GEN
    0.38
     kopp
    0.38
    exclude
    0.38
    excluded
    0.38
    Any
    0.37
    treated
    0.37
    POSITIVE LOGITS
    鰱
    0.39
     ఆడ
    0.39
    嬂
    0.39
    hasilan
    0.38
     производстве
    0.38
    书城
    0.38
    iería
    0.38
     প্যা
    0.37
     Indianapolis
    0.37
    oldsymbol
    0.37
    Activations Density 0.002%

    No Known Activations