© 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. 9633
    Prev
    Next
    INDEX
    Explanations

    transparent AstraZeneca

    np_acts-logits-general · gemini-2.5-flash-lite

    geometric coordinates in computer graphics notation, particularly x, y values in SVG, 3D models, and technical drawings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    向量
    -0.82
    }]{
    -0.82
     Confirm
    -0.82
    elected
    -0.82
    👇
    -0.81
     फ
    -0.79
    коны
    -0.79
     רק
    -0.79
     Draht
    -0.77
     (
    -0.76
    POSITIVE LOGITS
    momento
    0.87
    vielen
    0.86
    Pio
    0.86
     sucedido
    0.85
    gruß
    0.85
    Vorte
    0.85
     Función
    0.83
    Tomasz
    0.83
    Problemas
    0.83
     établissement
    0.83
    Activations Density 0.004%

    No Known Activations