© 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. 13466
    Prev
    Next
    INDEX
    Explanations

    form validation, horizontal form, EMC, Stat

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

    The neuron fires on occurrences of the term “form” (in tags, class names, widget names, etc.) in code.

    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
    …(
    -1.04
     高校
    -0.91
     hacen
    -0.91
     vong
    -0.88
     koi
    -0.88
    letzt
    -0.88
     anunció
    -0.88
     emplace
    -0.87
     Tonnen
    -0.87
     communi
    -0.86
    POSITIVE LOGITS
    wię
    1.24
     &&
    1.05
    minLength
    1.05
    esinde
    1.04
    kuun
    1.02
     oficial
    1.02
     Deber
    0.99
    ilistic
    0.98
     oport
    0.96
    tiska
    0.95
    Activations Density 0.004%

    No Known Activations