© 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. 128620
    Prev
    Next
    INDEX
    Explanations

    / xhtml

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

    This neuron detects numeric version identifiers (number tokens) in HTML/XHTML DOCTYPE and related markup declarations.

    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
     It
    -2.30
     but
    -1.93
    ).
    -1.91
    ">
    -1.91
    вяза
    -1.84
    It
    -1.80
     For
    -1.80
     Any
    -1.77
     only
    -1.73
    ۠
    -1.73
    POSITIVE LOGITS
     greateſt
    1.94
    ↵
    1.83
    Wady
    1.77
     цветами
    1.76
     sorprender
    1.73
    sudadera
    1.66
    hörigen
    1.65
    垕
    1.64
    🏗
    1.63
     dezelve
    1.62
    Activations Density 0.008%

    No Known Activations