© 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. 72956
    Prev
    Next
    INDEX
    Explanations

    comfortable things people wear or use

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

    comfortable ride

    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
    ן
    0.91
    ق
    0.70
    에요
    0.65
    OpportunitiesBy
    0.60
    <unused570>
    0.60
    ج
    0.60
     tươi
    0.59
    `;
    0.59
    㮍
    0.59
    </h1>
    0.58
    POSITIVE LOGITS
     Komfort
    1.05
     comfy
    1.03
     uncomfortable
    0.99
     comfortable
    0.95
     komfort
    0.93
     comfort
    0.91
     Comfortable
    0.88
     комфор
    0.88
     confortable
    0.88
     discomfort
    0.85
    Activations Density 0.055%

    No Known Activations