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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20777
    Prev
    Next
    INDEX
    Explanations

    epilepsy, ε, eyelashes

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

    Greek letters in scientific or medical text, particularly in contexts related to epilepsy.

    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
    嘮
    -2.38
    Lalu
    -2.30
     wth
    -2.28
    尪
    -2.25
    quelize
    -2.20
     étend
    -2.19
     superfí
    -2.16
    鋮
    -2.13
    銠
    -2.13
     freio
    -2.09
    POSITIVE LOGITS
    </strong>
    2.78
    </h3>
    2.75
     When
    2.53
    d
    2.45
    している
    2.28
    ));
    2.22
    籐
    2.20
    varepsilon
    2.17
    ;
    2.13
    ᳝
    2.13
    Activations Density 0.005%

    No Known Activations