© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129769
    Prev
    Next
    INDEX
    Explanations

    mouse events or exiting

    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_22/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
    jame
    -0.88
    ทั้ง
    -0.85
     giebt
    -0.81
     correos
    -0.79
     Anschließend
    -0.79
    Conclusie
    -0.78
     trabalhar
    -0.78
    Clientes
    -0.77
     ecológico
    -0.77
     عليهم
    -0.77
    POSITIVE LOGITS
    although
    0.91
     []
    0.85
    LOYEES
    0.85
    痉
    0.85
    digkeit
    0.82
    nę
    0.80
    гъл
    0.79
     vader
    0.79
     vicissitudes
    0.79
     ané
    0.78
    Activations Density 0.055%

    No Known Activations