© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 191722
    Prev
    Next
    INDEX
    Explanations

    Ellen Degeneres, sparkle, exclusively concentrate

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

    code structures and abstract concepts

    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
     է
    0.60
     रिश्वत
    0.57
     використання
    0.54
    曩
    0.54
     〢
    0.53
     Ін
    0.53
     પાણી
    0.53
     조사
    0.52
     Ві
    0.50
     ବି
    0.50
    POSITIVE LOGITS
    '
    0.52
     rehabilit
    0.49
     distinctions
    0.47
     effectively
    0.46
     maxill
    0.46
    fallen
    0.45
     subjug
    0.45
     administrations
    0.44
     interprets
    0.44
    osha
    0.44
    Activations Density 0.000%

    No Known Activations