© 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. 61289
    Prev
    Next
    INDEX
    Explanations

    browser support and issues

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

    browser does not support

    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
     subsid
    0.40
    technology
    0.39
     থাকি
    0.39
    zebra
    0.38
    ocaly
    0.38
    owntown
    0.38
    cell
    0.37
     "~/
    0.37
    ibi
    0.37
    edu
    0.36
    POSITIVE LOGITS
     Tatsache
    0.43
    ﺭ
    0.43
     miejsce
    0.41
    uß
    0.41
    अन्य
    0.41
     Faktoren
    0.40
     attempted
    0.40
    俘
    0.39
     overloading
    0.39
    ի
    0.39
    Activations Density 0.000%

    No Known Activations