© 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. 22167
    Prev
    Next
    INDEX
    Explanations

    HTML attribute assignments

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

    The neuron fires on numeric literals (digit sequences) embedded in HTML attribute values (e.g. href or src).

    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
    }
    -2.42
    </h3>
    -2.33
    </h1>
    -1.96
    ,”
    -1.95
    ”
    -1.78
     “
    -1.69
     tatuajes
    -1.57
    <i>
    -1.50
    keyboardType
    -1.42
     accomplishing
    -1.41
    POSITIVE LOGITS
     to
    2.20
    烀
    1.76
     fueron
    1.56
     Svizzera
    1.54
     Externe
    1.48
     svoju
    1.48
     dichas
    1.47
    饌
    1.45
     добавил
    1.45
     misalnya
    1.39
    Activations Density 0.006%

    No Known Activations