© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61143
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     повышение
    0.53
    폄
    0.46
    IR
    0.45
    low
    0.44
    MktCap
    0.44
     wcześ
    0.43
     Irina
    0.43
    捎
    0.43
     かわいい
    0.43
     frowning
    0.43
    POSITIVE LOGITS
    ،
    0.45
     place
    0.42
     INSERT
    0.41
    ，
    0.41
    [@
    0.40
     handlers
    0.40
    Dip
    0.40
    нить
    0.39
     she
    0.38
     разу
    0.38
    Activations Density 0.005%

    No Known Activations