© 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. 169686
    Prev
    Next
    INDEX
    Explanations

    understanding when

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

    cause/appears

    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
    秵
    0.56
    Ⲥ
    0.54
    ಿದ್ದೇವೆ
    0.51
    点で
    0.51
    لبية
    0.51
     azonban
    0.50
    َاب
    0.50
    ടതി
    0.50
     Україні
    0.49
    ാമ
    0.49
    POSITIVE LOGITS
    io
    0.63
    Dimension
    0.56
    IO
    0.54
    X
    0.53
    LL
    0.52
     BC
    0.52
    ollar
    0.51
    _
    0.51
    JavaScript
    0.50
    Her
    0.50
    Activations Density 0.000%

    No Known Activations