© 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. 10-GEMMASCOPE-RES-131K
    7. 29149
    Prev
    Next
    INDEX
    Explanations

    Cheshire, spire, diphtheria, UHF, paraiso

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

    names of English counties and regions, particularly Cheshire.

    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_10/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
    柃
    -3.11
    ⸂
    -2.83
    งิน
    -2.77
    蹕
    -2.72
    푆
    -2.69
    鮠
    -2.67
    樒
    -2.64
     saluti
    -2.63
    䛗
    -2.63
     ferrovia
    -2.53
    POSITIVE LOGITS
    </i>
    3.28
    that
    2.83
     появля
    2.78
    </h1>
    2.66
    That
    2.59
     ...
    2.42
     conocemos
    2.34
    <i>
    2.33
    </h5>
    2.28
    2.25
    Activations Density 0.002%
    No Known Activations