© 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. 105263
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific concepts

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

    ancient origins and simple explanations

    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
     G
    0.72
     L
    0.61
     D
    0.60
     N
    0.59
     H
    0.57
     Chicago
    0.55
     bats
    0.54
     J
    0.54
     V
    0.54
     E
    0.53
    POSITIVE LOGITS
    口座
    0.54
    нутри
    0.53
    givers
    0.52
    呟
    0.49
    つの
    0.48
    σό
    0.48
    pciones
    0.48
    プログラム
    0.47
     русских
    0.47
    ॉक्स
    0.47
    Activations Density 0.002%

    No Known Activations