© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176203
    Prev
    Next
    INDEX
    Explanations

    trouble insuit inby

    np_acts-logits-general · gemini-2.5-flash-lite

    what questions about prior actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    髗
    0.46
    転車
    0.45
    ر
    0.44
    ਕ
    0.44
    enetr
    0.44
    larghezza
    0.43
    र
    0.43
    たっぷ
    0.43
    軲
    0.43
    櫸
    0.42
    POSITIVE LOGITS
     Prelude
    0.48
     rối
    0.46
     Zack
    0.44
     Bxd
    0.43
     các
    0.43
     CMS
    0.41
     Jeff
    0.41
     Tan
    0.41
     मुआवजा
    0.41
     UAS
    0.40
    Activations Density 0.001%

    No Known Activations