© 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. 249120
    Prev
    Next
    INDEX
    Explanations

    running | allegations | from | expect | site | acoustic | equation | life | during

    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
    
    0.46
    ﾘ
    0.46
    梂
    0.46
     прежде
    0.45
     пле
    0.45
    ौरी
    0.43
    
    0.43
    剻
    0.42
     semuanya
    0.42
     VESSELS
    0.42
    POSITIVE LOGITS
    5
    0.50
     electronic
    0.50
     system
    0.47
     OPPO
    0.47
     bedre
    0.47
     opponent
    0.46
     महंगी
    0.46
     principes
    0.46
     assumption
    0.45
     multiple
    0.44
    Activations Density 0.000%

    No Known Activations