© 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-262K
    7. 80361
    Prev
    Next
    INDEX
    Explanations

    organization, gifts, multiple

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     costitu
    0.49
    ncnc
    0.48
     depots
    0.47
     Appropriations
    0.45
     Ocak
    0.44
     امرأة
    0.44
     vidhan
    0.44
    賤
    0.44
    خلي
    0.43
     tịch
    0.43
    POSITIVE LOGITS
    关注
    0.45
    [
    0.44
    Sustainable
    0.41
    Воз
    0.41
     pedagogical
    0.41
    These
    0.41
    ivalence
    0.41
    EM
    0.40
    Ping
    0.40
    SR
    0.40
    Activations Density 0.004%

    No Known Activations