© 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. 3133
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
     Uniform
    0.30
    আনু
    0.30
     Merchandise
    0.29
     Kaffee
    0.29
    အချိန်
    0.29
     Mexican
    0.28
     Gallows
    0.28
     Batterie
    0.28
     precinct
    0.28
     ></
    0.28
    POSITIVE LOGITS
    図
    0.35
    ष्मा
    0.32
    ड
    0.32
    Paula
    0.32
    у
    0.31
     вовсе
    0.30
    क
    0.30
    ност
    0.30
    טא
    0.30
     ጥላ
    0.30
    Activations Density 0.003%

    No Known Activations