© 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. 172260
    Prev
    Next
    INDEX
    Explanations

    It means

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

    code snippets and structured data

    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
     सॉरी
    0.52
     ۴
    0.50
     माफी
    0.49
    ổng
    0.48
     artific
    0.48
     இரண்ட
    0.48
     seni
    0.48
     cricketers
    0.48
     alloys
    0.47
     স্থলে
    0.47
    POSITIVE LOGITS
    Disney
    0.57
    K
    0.54
    Ev
    0.54
    Nach
    0.51
    Finn
    0.51
    U
    0.50
    Utah
    0.49
    These
    0.49
    Param
    0.48
    Men
    0.48
    Activations Density 0.000%

    No Known Activations