© 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. 58399
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and punctuation

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

    code starter or qualifier

    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
    簀
    0.49
    푅
    0.47
    ᱶ
    0.47
    اضره
    0.45
    Indent
    0.45
    GRE
    0.45
     indo
    0.44
     મુ
    0.44
    を持って
    0.44
    )}^{\
    0.43
    POSITIVE LOGITS
    il
    0.59
    ↵↵
    0.54
    im
    0.52
    ↵↵↵
    0.51
    ↵↵↵↵
    0.50
    ก
    0.49
    *
    0.46
    ual
    0.45
    orak
    0.45
    yl
    0.43
    Activations Density 0.000%

    No Known Activations