© 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. 49117
    Prev
    Next
    INDEX
    Explanations

    When followed by pronoun

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

    Socrates asked conditional questions

    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
     discre
    0.48
     класса
    0.46
    лия
    0.43
    ита
    0.43
     영향을
    0.42
    濘
    0.42
     호텔
    0.41
    icaria
    0.41
    ин
    0.40
     влия
    0.40
    POSITIVE LOGITS
     بە
    0.44
     humorous
    0.44
    ยน
    0.43
    🚲
    0.43
     رجال
    0.43
    भीत
    0.42
    フィルム
    0.42
    ifiés
    0.42
    wand
    0.42
     ricos
    0.42
    Activations Density 0.000%

    No Known Activations