© 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. 104588
    Prev
    Next
    INDEX
    Explanations

    Public Administration, Myocardial

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

    headers or section titles at the beginning of documents, particularly those containing dates or numerical information.

    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
     so
    -1.73
     more
    -1.66
     from
    -1.65
     everything
    -1.59
    Exer
    -1.55
     berühm
    -1.52
     verschillende
    -1.47
     about
    -1.47
     two
    -1.46
     every
    -1.45
    POSITIVE LOGITS
    诨
    1.69
     vider
    1.63
     milliard
    1.62
    Either
    1.61
     intelligente
    1.56
    ❣
    1.56
    😮
    1.53
     GRATU
    1.51
    itaire
    1.50
     IBRARY
    1.48
    Activations Density 0.000%

    No Known Activations