© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 8286
    Prev
    Next
    INDEX
    Explanations

    function definitions and calling

    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/layer_40_width_262k_l0_medium
    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
     oatmeal
    0.35
     پلان
    0.35
     خیلی
    0.35
     Semaphore
    0.32
     Apica
    0.32
     bitOp
    0.32
     '-')
    0.32
     Oatmeal
    0.31
     *)&
    0.30
     TouchUtils
    0.30
    POSITIVE LOGITS
     presented
    0.34
    un
    0.33
    র
    0.32
    owska
    0.30
    funktion
    0.30
    weeks
    0.29
     announced
    0.29
    difficulty
    0.29
     unveiled
    0.29
     मालम
    0.29
    Activations Density 1.423%

    No Known Activations