© 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. 187324
    Prev
    Next
    INDEX
    Explanations

    new installation

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

    introspection, physical conditions, commands

    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
     Relation
    0.53
     tät
    0.50
     tent
    0.49
     použ
    0.48
     yards
    0.48
     tents
    0.48
    ด
    0.46
     appliquer
    0.46
     Valence
    0.46
     nouns
    0.45
    POSITIVE LOGITS
    ^{-\
    0.46
    inclusive
    0.44
    Forgery
    0.44
    ुलिस
    0.43
    Ნ
    0.43
    old
    0.42
    不行
    0.42
     своя
    0.42
    it
    0.41
    Ac
    0.41
    Activations Density 0.001%

    No Known Activations