© 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. 239119
    Prev
    Next
    INDEX
    Explanations

    preserved mosaics, structured data, visitors centre

    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
     течение
    0.48
     휘
    0.45
    );\
    0.45
    縝
    0.45
    vär
    0.44
    гъл
    0.44
     излу
    0.43
    ไหล
    0.43
    룬
    0.42
    ುತ್ತಿರುವ
    0.41
    POSITIVE LOGITS
     defra
    0.53
     fraud
    0.51
    iOS
    0.48
    DefaultFor
    0.43
    意外
    0.42
     husbandry
    0.42
    Typography
    0.42
     surprising
    0.42
     TokenType
    0.41
    6
    0.41
    Activations Density 0.000%

    No Known Activations