© 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. 63573
    Prev
    Next
    INDEX
    Explanations

    judged more, decision tree, choice

    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
     apunt
    0.52
     fiscal
    0.51
     Esports
    0.50
     const
    0.50
    ↵
    0.49
     two
    0.48
     Archived
    0.48
     (=
    0.48
     envis
    0.47
     just
    0.46
    POSITIVE LOGITS
    vaa
    0.49
    Bei
    0.47
    reta
    0.47
    шенный
    0.47
    tetra
    0.46
    𝗕
    0.45
    رت
    0.45
    Prep
    0.45
    ADY
    0.45
    Bai
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.