© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2793
    Prev
    Next
    INDEX
    Explanations

    weight and quantities

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recession
    0.48
     विचारधारा
    0.43
     ނ
    0.42
     ставок
    0.40
     விரிவா
    0.40
    ရား
    0.40
     Fintech
    0.40
    广
    0.39
     ValidationError
    0.39
     Percolation
    0.39
    POSITIVE LOGITS
     weight
    2.91
    Weight
    2.61
    weight
    2.53
     Weight
    2.52
    重量
    2.52
     weights
    2.47
     weigh
    2.45
     WEIGHT
    2.41
     weighs
    2.39
     वजन
    2.38
    Activations Density 0.131%

    No Known Activations