© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22194
    Prev
    Next
    INDEX
    Explanations

    http, https, URLs

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

    The neuron fires on numeric tokens—especially citation numbers, years, volume/page numbers, and other bibliographic reference digits.

    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
     rápidas
    -1.41
    циях
    -1.38
    žas
    -1.34
    )
    -1.32
    owymi
    -1.32
     Nucleic
    -1.28
    🌶
    -1.28
     stitch
    -1.28
    owanie
    -1.27
    folgung
    -1.26
    POSITIVE LOGITS
     {
    1.50
    “
    1.47
    而非
    1.46
     einzigen
    1.41
    1.41
     как
    1.40
    like
    1.34
     Of
    1.33
     другими
    1.31
    please
    1.30
    Activations Density 0.167%
    No Known Activations