© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30493
    Prev
    Next
    INDEX
    Explanations

    French Formal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    设施
    0.42
     Tsuen
    0.42
    त्रेयी
    0.42
     pInBuffer
    0.42
     deactivated
    0.41
     Radiat
    0.40
    timevals
    0.40
    园
    0.40
     Tsuk
    0.39
    aparikkh
    0.38
    POSITIVE LOGITS
     survey
    0.55
     Survey
    0.44
    Survey
    0.44
    調査
    0.42
    目安
    0.41
     encuesta
    0.41
    survey
    0.40
     SURVEY
    0.40
     OECD
    0.39
    実感
    0.38
    Activations Density 0.001%

    No Known Activations