© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11586
    Prev
    Next
    INDEX
    Explanations

    HTML input attributes

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

    HTML input elements with a type attribute set to "text".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of HTML input elements whose type attribute is “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
    ۹
    -1.64
    mathrm
    -1.60
    你可以
    -1.55
    </h2>
    -1.54
    ſtra
    -1.47
    ۲
    -1.47
    ⁉
    -1.47
    ۶
    -1.45
    下的
    -1.43
     TON
    -1.42
    POSITIVE LOGITS
     in
    2.83
     of
    2.27
     on
    2.20
     for
    1.83
     across
    1.80
     into
    1.77
     they
    1.61
     towards
    1.56
     inside
    1.54
     along
    1.51
    Activations Density 0.005%

    No Known Activations