© 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. 34843
    Prev
    Next
    INDEX
    Explanations

    defeating opponents

    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
    },[])
    -0.94
     penyanyi
    -0.93
     my
    -0.92
    clinical
    -0.90
     ymin
    -0.85
    #######
    -0.84
     Athenians
    -0.83
    TRAILING
    -0.82
    你的
    -0.82
     приготовить
    -0.77
    POSITIVE LOGITS
    相手の
    0.91
     afectan
    0.87
     sufren
    0.82
     seleccionadas
    0.79
     acompañado
    0.79
     fellow
    0.79
    對方
    0.77
     requieren
    0.77
    知り
    0.77
     proporcionan
    0.76
    Activations Density 0.089%

    No Known Activations