© 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. 44978
    Prev
    Next
    INDEX
    Explanations

    sharing variables and values

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

    shared state management

    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
    Predictions
    0.46
    ⿺
    0.44
    olverine
    0.43
    ਦ
    0.43
    ੩
    0.43
    schemaLocation
    0.42
    Illinois
    0.41
     დაბ
    0.41
    bodyParser
    0.41
    崛
    0.41
    POSITIVE LOGITS
     createContext
    0.52
     Global
    0.46
    共享
    0.46
     de
    0.46
     compartir
    0.46
     state
    0.45
     shared
    0.45
     provides
    0.45
     alun
    0.44
     decre
    0.43
    Activations Density 0.002%

    No Known Activations