© 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. 20629
    Prev
    Next
    INDEX
    Explanations

    parenthetical citations followed by closing punctuation

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

    citations, years in parentheses

    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
     कार्या
    0.50
     crucially
    0.43
     whose
    0.42
    mea
    0.41
    ं
    0.41
    mc
    0.39
     pathogenesis
    0.39
     investigates
    0.39
    
    0.39
     associate
    0.39
    POSITIVE LOGITS
    leyball
    0.47
     게임
    0.46
    📌
    0.45
    <unused9>
    0.45
     사이즈
    0.44
    ленной
    0.43
    flin
    0.43
     myFunction
    0.43
    ઉન
    0.42
    luğ
    0.42
    Activations Density 0.013%

    No Known Activations