© 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. 153907
    Prev
    Next
    INDEX
    Explanations

    highest standards

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

    alpha, code, deep, setting descriptions

    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
    秶
    0.49
    暊
    0.49
     elucidated
    0.47
     αλλά
    0.47
    နှင့်
    0.46
    がありますが
    0.45
    →</
    0.44
     giờ
    0.43
     oi
    0.43
    琟
    0.42
    POSITIVE LOGITS
    test
    0.54
    store
    0.50
    liners
    0.49
    federal
    0.49
    women
    0.49
     poteva
    0.48
    频道
    0.48
    lar
    0.48
    freq
    0.48
    crime
    0.48
    Activations Density 0.000%

    No Known Activations