© 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. 39028
    Prev
    Next
    INDEX
    Explanations

    words starting with cur

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

    cur, cure, cursor, curl

    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
    س
    0.78
    ת
    0.65
     extender
    0.61
     tegas
    0.59
    น
    0.59
    ன்
    0.58
     reso
    0.55
    ir
    0.54
    תר
    0.54
     eröff
    0.53
    POSITIVE LOGITS
    cur
    0.79
     кури
    0.78
     Curiosity
    0.78
    CUR
    0.73
     curvatures
    0.71
    9
    0.70
     CURL
    0.68
     CUR
    0.68
     curate
    0.68
     curved
    0.67
    Activations Density 0.050%

    No Known Activations