© 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. 114030
    Prev
    Next
    INDEX
    Explanations

    the.to

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

    technical documentation and explanations

    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
    Warum
    0.49
     динами
    0.48
    APPED
    0.47
    Mys
    0.47
    朳
    0.47
    ENCES
    0.46
     тобі
    0.46
    YNAMIC
    0.45
    లోనే
    0.44
    捱
    0.44
    POSITIVE LOGITS
     inoxydable
    0.50
     trem
    0.49
    id
    0.48
    rochemical
    0.47
    <unused60>
    0.46
    ";
    0.46
     og
    0.46
     ore
    0.46
     matte
    0.46
    ifting
    0.46
    Activations Density 0.000%

    No Known Activations