© 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. 219193
    Prev
    Next
    INDEX
    Explanations

    specific actions preceding entities

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

    mode decomposition

    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
    ामान्य
    0.52
     구현
    0.51
     ふ
    0.49
     cải
    0.48
    GlobalSection
    0.48
     تعمیر
    0.48
     thuế
    0.48
     遅く
    0.47
    䢀
    0.47
     かわ
    0.46
    POSITIVE LOGITS
    ussa
    0.50
    illi
    0.46
    rx
    0.46
     Elias
    0.46
    yst
    0.45
     I
    0.44
    oy
    0.43
    itha
    0.43
     stock
    0.43
    enan
    0.43
    Activations Density 0.001%

    No Known Activations