© 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. 124309
    Prev
    Next
    INDEX
    Explanations

    national standard

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

    iambic pentameter

    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
    ())))
    0.48
    ürü
    0.47
    Гу
    0.47
    Gü
    0.47
    geojson
    0.46
    {-#
    0.45
    拡
    0.45
     парла
    0.45
    %%%%%%%%%%%%%
    0.45
    žič
    0.45
    POSITIVE LOGITS
    ب
    0.52
     questões
    0.46
     TASK
    0.45
     defective
    0.45
    ف
    0.44
     Angleterre
    0.43
     assumptions
    0.43
     الم
    0.42
     textbox
    0.42
    م
    0.41
    Activations Density 0.001%

    No Known Activations