© 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. 128168
    Prev
    Next
    INDEX
    Explanations

    certified by

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

    founding or defining aspect

    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
    地位
    0.56
    倘
    0.50
    )}^{
    0.48
    迭代
    0.48
    جمالي
    0.46
    爬
    0.46
    豈
    0.46
     valiant
    0.45
     totalité
    0.44
    _{-}^{
    0.44
    POSITIVE LOGITS
    da
    0.56
    uş
    0.54
    inj
    0.52
    나
    0.52
     Ө
    0.51
    mato
    0.50
    pora
    0.49
     langen
    0.48
     ۱۰
    0.47
    lara
    0.47
    Activations Density 0.000%

    No Known Activations