© 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. 34-GEMMASCOPE-RES-131K
    7. 92745
    Prev
    Next
    INDEX
    Explanations

    xaml and ms namespace declarations

    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_34/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
     Tö
    -0.88
    apikey
    -0.85
     Bunun
    -0.82
     İlk
    -0.79
    三菱
    -0.79
     vegetable
    -0.78
     Çünkü
    -0.77
    …！
    -0.76
     equipa
    -0.75
    運輸
    -0.73
    POSITIVE LOGITS
     angebracht
    0.93
    lenül
    0.91
    pF
    0.88
    跸
    0.86
     conclusão
    0.85
     того
    0.84
    ueger
    0.84
    ленным
    0.84
     evaluaciones
    0.84
    触摸
    0.84
    Activations Density 0.002%

    No Known Activations