© 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. 71486
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

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

    ssh keys or scope

    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
     प्रतिस्पर्धा
    0.46
     उत्पन्न
    0.45
    ٥
    0.44
     स्थिति
    0.44
     социа
    0.44
    調
    0.44
     گروه
    0.43
     बने
    0.42
    誰
    0.42
    ذ
    0.42
    POSITIVE LOGITS
    
    0.50
     DAS
    0.49
     roommates
    0.47
    ikti
    0.47
    
    0.47
    ริ่ม
    0.46
     indiquée
    0.46
     tasty
    0.46
     naturelle
    0.46
     eût
    0.46
    Activations Density 0.000%

    No Known Activations