Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 473
    Prev
    Next
    INDEX
    Explanations

    biomedical databases

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

    references to scientific databases and bioinformatics resources like GenBank, NCBI, PubMed, and UniProt.

    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
     It
    -1.85
    ();
    -1.64
     Then
    -1.55
    </h3>
    -1.52
    </em>
    -1.52
    The
    -1.51
    );
    -1.50
     Important
    -1.48
     Any
    -1.45
     The
    -1.45
    POSITIVE LOGITS
    Дмитрий
    1.85
    Максим
    1.84
     reacties
    1.73
     telles
    1.70
    Марина
    1.68
     手绘
    1.67
     farmacé
    1.66
     halen
    1.61
     comentários
    1.54
     soste
    1.54
    Activations Density 0.026%

    No Known Activations