© 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. 135219
    Prev
    Next
    INDEX
    Explanations

    PR card renewal

    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
    m
    0.63
     आ
    0.48
    म
    0.46
     arid
    0.46
    ম
    0.46
    ব
    0.45
     Boyd
    0.45
     Angles
    0.45
    q
    0.45
    ტ
    0.45
    POSITIVE LOGITS
     stranger
    0.44
     configure
    0.41
     أول
    0.39
     لا
    0.38
     convocatoria
    0.38
     build
    0.38
     oversight
    0.38
    駆け
    0.38
    ത്തിയത്
    0.37
     wash
    0.37
    Activations Density 0.006%

    No Known Activations