© 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. 14252
    Prev
    Next
    INDEX
    Explanations

    closing, closed, or close-up concepts

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

    close or closed

    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
     Says
    0.55
     odstr
    0.55
     azalt
    0.55
     Appel
    0.54
     เรีย
    0.54
    ى
    0.54
    ితీ
    0.52
     (
    0.52
     It
    0.52
     OR
    0.52
    POSITIVE LOGITS
     clos
    1.27
     closed
    1.23
    close
    1.23
    閉
    1.23
    CLOSE
    1.22
     close
    1.18
     closure
    1.13
     closing
    1.13
     близь
    1.09
    封闭
    1.09
    Activations Density 0.058%

    No Known Activations