© 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. 100939
    Prev
    Next
    INDEX
    Explanations

    genes, alleles, and infection

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

    HTML-style formatting tags and publication titles in italics or other special formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron responds to formatting and emphasis markers (italic tags, asterisks, underscores, etc.) surrounding titles or emphasized text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     them
    -1.45
     theres
    -1.37
     even
    -1.30
     expands
    -1.28
    也有
    -1.27
     Seidel
    -1.26
    主流
    -1.21
     bahkan
    -1.20
     first
    -1.19
     Ström
    -1.17
    POSITIVE LOGITS
    thwaite
    1.33
     erectile
    1.30
    --
    1.28
     kjent
    1.28
     penis
    1.25
    aktionen
    1.24
    偏偏
    1.23
    1.23
    "}}>
    1.23
     pēc
    1.23
    Activations Density 0.017%

    No Known Activations