© 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. 23003
    Prev
    Next
    INDEX
    Explanations

    skilled guys

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

    disease, war, reaction

    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
    मारा
    0.57
    ni
    0.56
     Ural
    0.51
    вни
    0.51
    ни
    0.50
     पढ़ने
    0.50
    <strong>
    0.50
     Biden
    0.49
     Ahmet
    0.49
     favors
    0.49
    POSITIVE LOGITS
    ជំងឺ
    0.54
     நோய்
    0.50
     لڑکی
    0.49
     Chiến
    0.49
     بیماری
    0.47
     guérison
    0.47
    公主
    0.43
    箪
    0.43
    窈
    0.43
     전투
    0.42
    Activations Density 0.000%

    No Known Activations