© 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. 135235
    Prev
    Next
    INDEX
    Explanations

    used, using, or changing

    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
     желе
    0.48
     tetrachloride
    0.46
     μέσα
    0.46
    PathTemplate
    0.45
    كتر
    0.45
     ஏரா
    0.45
     పర
    0.45
     τύ
    0.45
    妷
    0.44
     sepatu
    0.43
    POSITIVE LOGITS
    est
    0.56
     phrases
    0.48
    不
    0.47
     practice
    0.46
     misuse
    0.44
    romptu
    0.44
    وم
    0.44
    will
    0.44
     note
    0.43
    SM
    0.43
    Activations Density 0.003%

    No Known Activations