© 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. 58256
    Prev
    Next
    INDEX
    Explanations

    form control

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

    This neuron fires on the HTML/CSS token “form” when it appears in class names or tags—e.g. Bootstrap’s “form-group,” “form-control,” and <form> elements.

    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
     misleading
    -0.81
    Pranala
    -0.81
    क्टर
    -0.79
    Jenis
    -0.78
    🎦
    -0.76
    álen
    -0.74
    êcher
    -0.73
     Being
    -0.73
    Presentación
    -0.72
     matter
    -0.72
    POSITIVE LOGITS
    control
    1.91
    CONTROL
    1.77
    Control
    1.70
     control
    1.65
     Control
    1.56
     CONTROL
    1.54
     Kontrolle
    1.18
     controle
    1.16
     kontrol
    1.13
    控制
    1.12
    Activations Density 0.003%

    No Known Activations