© 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. 14824
    Prev
    Next
    INDEX
    Explanations

    HTML attributes like id, name, style

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

    The neuron fires on numeric literals (e.g. digits, pixel values, IDs, version numbers) embedded in HTML attribute values.

    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
     by
    -2.11
     všem
    -1.52
     trataba
    -1.43
    خفض
    -1.41
     gedurende
    -1.40
     белом
    -1.30
     explosión
    -1.29
     priceless
    -1.28
     geniales
    -1.27
     男孩
    -1.26
    POSITIVE LOGITS
    “
    1.79
     is
    1.65
     we
    1.61
    A
    1.55
     ؛
    1.52
    U
    1.43
    <
    1.38
    achen
    1.32
    h
    1.31
    „
    1.31
    Activations Density 0.004%

    No Known Activations