© 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. 75289
    Prev
    Next
    INDEX
    Explanations

    chromosomal locations

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

    alphanumeric identifiers like Q numbers and chromosome locations.

    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
     They
    -2.05
     but
    -1.95
     to
    -1.83
    yyb
    -1.75
     permitirá
    -1.75
     แต่
    -1.71
     You
    -1.67
    ForValue
    -1.67
     agregó
    -1.67
     But
    -1.59
    POSITIVE LOGITS
    Was
    1.73
    Tr
    1.65
     baskılı
    1.63
    id
    1.62
    Do
    1.61
     connu
    1.59
    sto
    1.58
    Ver
    1.58
     baik
    1.58
    out
    1.57
    Activations Density 0.038%

    No Known Activations