© 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. 138862
    Prev
    Next
    INDEX
    Explanations

    bay and spins

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

    good answer 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
    т
    0.52
    硒
    0.51
    гән
    0.50
     Leach
    0.46
    iénd
    0.46
    吅
    0.44
     러
    0.44
     карка
    0.44
    itação
    0.44
     Painter
    0.44
    POSITIVE LOGITS
     jed
    0.50
     dvou
    0.49
     velmi
    0.48
    <0x8B>
    0.47
    不错
    0.46
     อืม
    0.46
     bonnes
    0.46
     sv
    0.46
     bagels
    0.46
    買い
    0.46
    Activations Density 0.000%

    No Known Activations