© 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. 159252
    Prev
    Next
    INDEX
    Explanations

    Blue Brown Color Watch Descriptions

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

    identifying potential typos

    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
    蒾
    0.52
     દરમ
    0.51
    ᆺ
    0.48
    politik
    0.48
    {$
    0.47
    ojs
    0.47
     よ
    0.47
    vní
    0.46
     ザ
    0.46
    kamp
    0.46
    POSITIVE LOGITS
     Precipitation
    0.44
    ном
    0.44
     относятся
    0.43
    ник
    0.42
    Suit
    0.42
    ляр
    0.40
     firearms
    0.40
    也是
    0.40
    ственно
    0.39
    PQ
    0.39
    Activations Density 0.000%

    No Known Activations