© 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. 125161
    Prev
    Next
    INDEX
    Explanations

    rules, changes, while, line, deciding

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

    describing representation or function

    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
    d
    0.48
    х
    0.48
    सा
    0.47
    haya
    0.47
    ਜ
    0.46
    ires
    0.45
    hj
    0.45
    伊
    0.45
     (
    0.45
    ri
    0.45
    POSITIVE LOGITS
     governs
    0.49
     allError
    0.49
     euer
    0.48
     [,
    0.46
     millennia
    0.46
     объем
    0.46
     batalla
    0.45
    摄像
    0.45
     escánd
    0.44
    厮
    0.44
    Activations Density 0.000%

    No Known Activations