© 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. 158861
    Prev
    Next
    INDEX
    Explanations

    collection, subjects, resolution

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

    words before punctuation or specific phrases

    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
    点は
    0.49
    autoref
    0.47
     diez
    0.47
    Pope
    0.46
     fehl
    0.45
    V
    0.45
    ɗ
    0.45
    flow
    0.45
    failure
    0.45
    l
    0.44
    POSITIVE LOGITS
     ស
    0.52
     Atti
    0.48
     கு
    0.47
     Université
    0.47
     skis
    0.46
     Ét
    0.45
     πα
    0.44
     Eph
    0.44
     baskets
    0.44
     지하
    0.43
    Activations Density 0.000%

    No Known Activations