© 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. 57393
    Prev
    Next
    INDEX
    Explanations

    behind his, Two prevailing

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

    literal translation

    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
    st
    0.58
    सी
    0.57
    de
    0.52
    デ
    0.50
    ント
    0.48
    दे
    0.47
    ジ
    0.46
    シ
    0.46
     neden
    0.45
    odeon
    0.44
    POSITIVE LOGITS
    繖
    0.51
    =\{\
    0.50
     பெண்
    0.48
     الدراسة
    0.48
     ஆய்
    0.47
     ಅಧ್ಯ
    0.46
    foldername
    0.46
     документ
    0.45
     అధ్య
    0.44
    adır
    0.44
    Activations Density 0.000%

    No Known Activations