© 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. 63080
    Prev
    Next
    INDEX
    Explanations

    dates and reviews

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

    AI followed by dialogue markers

    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
    ამაშ
    0.45
    ங்கிய
    0.44
    asına
    0.44
     cristall
    0.43
    傳
    0.43
    以來
    0.43
    棿
    0.43
     retornar
    0.42
    მას
    0.41
    嫡
    0.41
    POSITIVE LOGITS
    OX
    0.47
     Similarly
    0.45
     Pueblo
    0.45
    POT
    0.44
    ORD
    0.44
     practices
    0.42
    CON
    0.41
     sidewalks
    0.41
    Tampa
    0.41
     _;
    0.41
    Activations Density 0.000%

    No Known Activations