© 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. 6878
    Prev
    Next
    INDEX
    Explanations

    foreign language text segments

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

    numbers, currency, and royal terms

    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
     skj
    0.50
     H
    0.49
     resumption
    0.49
     L
    0.48
     n
    0.48
     \
    0.47
     svar
    0.46
     ú
    0.46
     uden
    0.46
     visc
    0.46
    POSITIVE LOGITS
    <unused1063>
    0.52
    ર્સ
    0.49
    Tambah
    0.46
     ఆదాయ
    0.46
    І
    0.46
     уйнау
    0.46
     Сури
    0.45
    у
    0.44
    datatables
    0.44
    ╿
    0.44
    Activations Density 0.003%

    No Known Activations