© 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. 182374
    Prev
    Next
    INDEX
    Explanations

    delivery, production, errors

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

    medical injury fissure tear rupture

    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
    图片的
    0.46
     Liss
    0.41
    ণি
    0.40
    ’
    0.39
    s
    0.39
    的国家
    0.38
    <0xB5>
    0.38
    <0xB7>
    0.38
     ard
    0.38
    OfThe
    0.38
    POSITIVE LOGITS
     फीड
    0.54
     Акы
    0.51
     माइनस
    0.49
     सिक्योर
    0.49
    šit
    0.48
    araan
    0.48
     xlab
    0.48
    マット
    0.48
     prefque
    0.48
     सिंपल
    0.48
    Activations Density 0.000%

    No Known Activations