© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 98756
    Prev
    Next
    INDEX
    Explanations

    everywhere and anywhere

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

    anywhere & everywhere

    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
    b
    0.72
     Оно
    0.59
    m
    0.58
    f
    0.57
     Wirk
    0.54
     Че
    0.53
     భ
    0.52
    sproz
    0.52
    lasso
    0.52
    w
    0.52
    POSITIVE LOGITS
    abouts
    0.63
     everywhere
    0.63
    صی
    0.61
    دهای
    0.59
    ین
    0.59
     ailleurs
    0.58
    اداسی
    0.58
    ifrån
    0.57
    -
    0.57
     sekitar
    0.57
    Activations Density 0.059%

    No Known Activations