© 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. 219325
    Prev
    Next
    INDEX
    Explanations

    proper nouns and scientific terms

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

    combines, enhance, addition, simplified, assignment

    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
    Static
    0.57
    Payout
    0.57
    जिसे
    0.57
    Jeśli
    0.56
    拍卖
    0.56
    愿
    0.56
     спосо
    0.55
    萨
    0.55
     стаўкі
    0.53
    Legacy
    0.53
    POSITIVE LOGITS
     Mediterranean
    0.59
     bulan
    0.55
     October
    0.55
     bronchi
    0.54
     Britain
    0.54
     calcium
    0.54
     Bulan
    0.53
     redshift
    0.53
     Thames
    0.52
     astronomers
    0.52
    Activations Density 0.000%

    No Known Activations