© 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. 202047
    Prev
    Next
    INDEX
    Explanations

    linkCode

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

    historical context, time slots, or blurry descriptions

    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
     YOUR
    0.49
     tergantung
    0.46
    點
    0.45
    竊
    0.43
    會
    0.42
     azt
    0.41
    you
    0.41
    謝謝
    0.41
     fortsatt
    0.41
    ışı
    0.41
    POSITIVE LOGITS
    usky
    0.51
     remorse
    0.48
    𒉣
    0.47
    WindowClass
    0.47
    lovepoetry
    0.47
     innumerable
    0.46
    वश
    0.46
    ன்மையான
    0.46
    usin
    0.46
    ometime
    0.46
    Activations Density 0.003%

    No Known Activations