© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85108
    Prev
    Next
    INDEX
    Explanations

    amino acid sequences and biological compounds

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

    three-letter amino acid codes like Tyr, Lys, Val, Pro, Gln, and Leu in scientific contexts.

    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
     préstamos
    -1.69
     miniaturka
    -1.68
     investimentos
    -1.66
     jabón
    -1.65
     acrí
    -1.63
     rése
    -1.63
     reemplazo
    -1.62
    obrázek
    -1.61
    ᯾
    -1.59
     maravill
    -1.57
    POSITIVE LOGITS
     I
    1.92
    As
    1.73
    According
    1.72
     with
    1.70
    te
    1.69
     regarding
    1.64
    Not
    1.64
    With
    1.64
    from
    1.62
    Because
    1.61
    Activations Density 0.001%

    No Known Activations