© 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. 224510
    Prev
    Next
    INDEX
    Explanations

    time, if, bed, spelling

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

    societal biases

    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
    uya
    0.52
    uyu
    0.49
    ieli
    0.49
    psia
    0.45
    uları
    0.45
    uyi
    0.45
    údo
    0.45
    먼
    0.45
     ብዙ
    0.44
     भीषण
    0.44
    POSITIVE LOGITS
     offline
    0.45
     सिम
    0.43
    APOLIS
    0.42
     DEPEND
    0.41
     मानदंड
    0.41
     centrifuged
    0.41
    national
    0.40
    ENV
    0.40
     asyncHandler
    0.40
     "../
    0.39
    Activations Density 0.001%

    No Known Activations