© 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-262K
    7. 137616
    Prev
    Next
    INDEX
    Explanations

    list items and code snippets

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ړو
    0.40
    てもら
    0.40
     drown
    0.39
    篒
    0.39
    洸
    0.39
     ridicul
    0.38
     Möglich
    0.38
     sui
    0.38
    DeathRecord
    0.38
    陬
    0.37
    POSITIVE LOGITS
     전자
    0.39
    beek
    0.39
    자
    0.38
     jin
    0.38
     cycl
    0.38
     uży
    0.38
     вида
    0.37
    ண்ப
    0.37
    omena
    0.37
     પ્રે
    0.37
    Activations Density 0.000%

    No Known Activations