© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43903
    Prev
    Next
    INDEX
    Explanations

    HTML input types

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

    This neuron detects HTML “type=” attributes (most prominently on `<input>` tags).

    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
    n
    -2.06
     
    -1.77
    s
    -1.75
    使った
    -1.60
    ro
    -1.56
    _
    -1.53
    se
    -1.48
    特别是
    -1.42
    たたみ
    -1.39
     ストレッチ
    -1.39
    POSITIVE LOGITS
     what
    1.94
    錘
    1.71
     Despite
    1.66
     összefoglaló
    1.62
    Despite
    1.59
    煐
    1.56
     élector
    1.52
     Unlike
    1.52
    琤
    1.52
    toprule
    1.51
    Activations Density 0.004%

    No Known Activations