© 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. 35249
    Prev
    Next
    INDEX
    Explanations

    language identifiers and punctuation

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

    semicolon terminating list items

    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
    ل
    0.87
    يل
    0.84
    \
    0.83
    л
    0.80
     that
    0.79
    (
    0.75
    ona
    0.73
    }-\
    0.71
     analys
    0.71
    v
    0.71
    POSITIVE LOGITS
    ও
    1.20
    在
    1.02
    to
    1.01
    ע
    0.99
     in
    0.98
    도
    0.97
    もら
    0.90
    も
    0.89
    きた
    0.88
    ки
    0.86
    Activations Density 0.089%

    No Known Activations