© 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. 84391
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    ovat
    -0.90
     when
    -0.90
    wszy
    -0.87
    دانلود
    -0.81
     充電
    -0.81
     while
    -0.80
     продукт
    -0.79
    ایق
    -0.78
    ÜR
    -0.78
    vière
    -0.78
    POSITIVE LOGITS
    visuel
    1.08
    June
    0.93
     überhaupt
    0.92
    鈥
    0.92
     Einbau
    0.92
     Tenemos
    0.91
    phide
    0.91
     ALSO
    0.90
    tribune
    0.88
    鳞
    0.87
    Activations Density 0.004%

    No Known Activations