© 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. 123803
    Prev
    Next
    INDEX
    Explanations

    betting withhim with

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

    be taken

    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
    Negative Logits
    ഴിലാ
    0.50
     tablespoons
    0.49
     spoons
    0.49
     fieldContext
    0.47
    亩
    0.46
     tainted
    0.46
     końca
    0.45
     bhij
    0.44
     রানে
    0.44
     tubs
    0.43
    POSITIVE LOGITS
    noz
    0.50
     Er
    0.46
    zahl
    0.46
     A
    0.45
     Episcopal
    0.44
     Ehr
    0.44
    的过程
    0.44
    أي
    0.43
     Berc
    0.43
    一系列
    0.43
    Activations Density 0.000%

    No Known Activations