© 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. 2998
    Prev
    Next
    INDEX
    Explanations

    programming keywords and constructs

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

    go import statements

    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
    жні
    0.44
    쇤
    0.43
    жна
    0.41
     Leigh
    0.41
     digo
    0.41
     buttermilk
    0.41
    ﺎ
    0.40
     carcinogenic
    0.40
    льбе
    0.40
    ڍ
    0.40
    POSITIVE LOGITS
    un
    0.47
    import
    0.46
    os
    0.46
    on
    0.45
    if
    0.45
    can
    0.44
    im
    0.44
    {}
    0.44
    i
    0.43
    $$
    0.42
    Activations Density 0.000%

    No Known Activations