© 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. 15588
    Prev
    Next
    INDEX
    Explanations

    protein and Rac3

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

    protein and peptide

    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
    ستم
    0.41
    obenzene
    0.39
     Piccadilly
    0.39
    epin
    0.39
    罌
    0.39
    মিশ্র
    0.38
    rón
    0.38
     descuento
    0.37
    </tfoot>
    0.37
    边缘
    0.37
    POSITIVE LOGITS
     protein
    0.85
    Protein
    0.83
    protein
    0.77
     Proteins
    0.77
     Protein
    0.76
     proteins
    0.75
     प्रोटीन
    0.64
     proteínas
    0.63
    proteins
    0.63
    蛋白质
    0.62
    Activations Density 0.088%

    No Known Activations