© 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. 149738
    Prev
    Next
    INDEX
    Explanations

    segment where

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

    scope, concerns, executives, evidence, test

    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
     fastest
    0.50
    羰
    0.47
     fluorescent
    0.45
     electrodes
    0.45
     depositors
    0.44
     armies
    0.44
     flushed
    0.44
    IPOP
    0.44
     magia
    0.43
    λασ
    0.43
    POSITIVE LOGITS
    対象
    0.50
    した
    0.50
    
    0.48
    
    0.46
    姿勢
    0.43
    сут
    0.43
    有機
    0.43
    hitth
    0.43
     Defts
    0.42
    䙲
    0.42
    Activations Density 0.000%

    No Known Activations