© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21422
    Prev
    Next
    INDEX
    Explanations

    last year

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ఇటీవల
    0.42
     갑
    0.41
     franchise
    0.40
     편성
    0.39
     tên
    0.39
     tù
    0.38
     zl
    0.38
    ibi
    0.38
     Name
    0.37
    苳
    0.37
    POSITIVE LOGITS
     year
    0.46
    year
    0.43
    bcrypt
    0.41
     godinu
    0.41
     night
    0.40
     nights
    0.39
     generations
    0.39
    Jahr
    0.39
    (||
    0.39
     centuries
    0.38
    Activations Density 0.000%

    No Known Activations