© 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. 55992
    Prev
    Next
    INDEX
    Explanations

    demonic threat depictions

    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
     conceito
    0.57
    ي
    0.53
    ينا
    0.50
    चूर
    0.50
     аллер
    0.49
     cuanto
    0.49
    льзя
    0.48
     zwe
    0.48
    ប៉
    0.48
    Approach
    0.48
    POSITIVE LOGITS
     multiplication
    0.46
    鳝
    0.43
     Multiplication
    0.41
     I
    0.41
    H
    0.40
     Sewage
    0.39
     humble
    0.39
    -
    0.39
    スの
    0.38
     Sensors
    0.38
    Activations Density 0.001%

    No Known Activations