© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44048
    Prev
    Next
    INDEX
    Explanations

    oversight, Overwatch, SwiftUI, readout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    of
    -3.14
     There
    -2.52
     получила
    -2.39
    M
    -2.30
    re
    -2.23
    S
    -2.20
     видит
    -2.20
    2
    -2.16
     gespannt
    -2.16
    la
    -2.16
    POSITIVE LOGITS
     of
    3.89
    ༀ
    3.20
    揶
    2.73
    ｍ
    2.64
    
    2.63
     ferv
    2.56
    ');
    2.50
            
    2.47
    
    2.47
    をする
    2.44
    Activations Density 0.002%

    No Known Activations