© 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. 34-GEMMASCOPE-RES-131K
    7. 75751
    Prev
    Next
    INDEX
    Explanations

    supra shoes, FWD, virus

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

    special typographical characters like hyphens and brackets in text, particularly those used in technical or specialized formatting.

    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_34/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
    حص
    -0.89
     renewables
    -0.88
    edizione
    -0.79
     Kün
    -0.78
     sikre
    -0.75
    𝘦
    -0.73
     inoxydable
    -0.73
    愤
    -0.72
     هنری
    -0.72
     Castelo
    -0.71
    POSITIVE LOGITS
    扛
    0.77
    ût
    0.76
    英語版
    0.75
    श्यक
    0.74
    ższe
    0.74
    ้า
    0.73
    annel
    0.73
     fundación
    0.72
     zusätz
    0.71
    cope
    0.71
    Activations Density 0.004%

    No Known Activations