© 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. 77064
    Prev
    Next
    INDEX
    Explanations

    regarding participation

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

    polite inquiries and descriptions

    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
     Asa
    0.52
     inú
    0.52
     今天
    0.50
     Azerbai
    0.50
     anex
    0.50
     fachada
    0.49
    <unused98>
    0.49
     futuras
    0.48
     ഇന്ന്
    0.48
    竰
    0.48
    POSITIVE LOGITS
    Case
    0.50
    Ka
    0.49
    Disp
    0.49
    NC
    0.48
    Griff
    0.48
    Less
    0.48
    _
    0.48
    Code
    0.47
    DSM
    0.47
    ان
    0.47
    Activations Density 0.001%

    No Known Activations