© 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. 127376
    Prev
    Next
    INDEX
    Explanations

    PTA is, offers various, offering a

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

    scientific and cosmic origins

    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
    ním
    0.51
    <0x80>
    0.51
    ственный
    0.47
    resc
    0.47
     신
    0.47
     البح
    0.46
    だったら
    0.46
    (~
    0.45
     thự
    0.45
     земе
    0.44
    POSITIVE LOGITS
     Eck
    0.54
     Nutrient
    0.50
     Saba
    0.50
     Saints
    0.49
     karn
    0.49
     Victor
    0.49
     Nutrition
    0.47
     saints
    0.47
     samurai
    0.47
     Predicted
    0.46
    Activations Density 0.001%

    No Known Activations