© 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. 72326
    Prev
    Next
    INDEX
    Explanations

    used, available, dissolved

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

    how something is used

    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
    чні
    0.55
     დიდ
    0.52
    𒉈
    0.52
    𒋗
    0.50
     যুবক
    0.50
     ಸಂಧಿ
    0.50
     ў
    0.49
     своё
    0.49
    ベート
    0.48
    த்தினை
    0.48
    POSITIVE LOGITS
    ↵↵
    0.50
    pk
    0.47
     Heartland
    0.46
    dest
    0.46
    se
    0.45
    mer
    0.44
    so
    0.44
    test
    0.44
    l
    0.43
    dn
    0.43
    Activations Density 0.000%

    No Known Activations