© 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. 22-GEMMASCOPE-RES-131K
    7. 9590
    Prev
    Next
    INDEX
    Explanations

    submit button clicks

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

    The neuron activates on occurrences of “submit” (in HTML input/button attributes or jQuery form‐submit calls).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     amazing
    -1.21
     genellikle
    -1.18
     comportamento
    -1.17
     duża
    -1.17
     astounding
    -1.15
     immense
    -1.15
    咳咳
    -1.15
     predominantly
    -1.13
    感じで
    -1.11
    咦
    -1.10
    POSITIVE LOGITS
     hiper
    1.30
     perfecto
    1.30
     artesanal
    1.27
     rosado
    1.26
     anormal
    1.25
     vinagre
    1.24
     ensalada
    1.20
     combinaison
    1.19
     impecable
    1.18
     objectif
    1.17
    Activations Density 0.001%

    No Known Activations