© 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. 34-GEMMASCOPE-RES-131K
    7. 93335
    Prev
    Next
    INDEX
    Explanations

    HTML input types

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

    The neuron activates on HTML form input “type” attribute values (e.g. text, button, submit, hidden, number).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     皮肤
    -1.04
    敎
    -1.00
    ēja
    -0.93
     遇
    -0.92
     كندا
    -0.90
     个性
    -0.88
     Justiz
    -0.88
     seguinte
    -0.88
     selbst
    -0.87
    र्च
    -0.85
    POSITIVE LOGITS
     name
    1.26
     orquesta
    1.06
     kutu
    1.06
     reik
    1.00
     zove
    0.98
    alahkan
    0.97
     botines
    0.97
     annen
    0.97
     vårt
    0.96
     dring
    0.96
    Activations Density 0.003%

    No Known Activations