© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93121
    Prev
    Next
    INDEX
    Explanations

    specific keywords within code or text

    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
    衣装
    -0.77
    ọt
    -0.77
     automaticamente
    -0.75
     HttpResponse
    -0.74
     extraordinary
    -0.74
     noteworthy
    -0.73
     analysis
    -0.72
     paralelo
    -0.71
     Analyzed
    -0.70
    Análisis
    -0.69
    POSITIVE LOGITS
     Efek
    0.93
     Φ
    0.85
    Specific
    0.84
    specifically
    0.84
    kla
    0.81
    specific
    0.81
     BEGIN
    0.81
    naw
    0.81
     itself
    0.78
    cas
    0.78
    Activations Density 0.042%

    No Known Activations