© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245659
    Prev
    Next
    INDEX
    Explanations

    Affordability Passport®

    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
    мы
    0.61
    ጣጠ
    0.53
    }^{*}=\
    0.52
     undermined
    0.52
    ೃಷ್ಟ
    0.49
    Мы
    0.47
     организаций
    0.46
     சென்னைய
    0.46
    Ⅲ
    0.45
     deshalb
    0.45
    POSITIVE LOGITS
     Colors
    0.62
     Farben
    0.56
     Colours
    0.54
     চালান
    0.54
     particolari
    0.52
     remplacer
    0.50
     JDK
    0.50
     Coloring
    0.49
     Jul
    0.49
     colores
    0.49
    Activations Density 0.000%

    No Known Activations