© 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. 54105
    Prev
    Next
    INDEX
    Explanations

    UI element identifiers

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

    The neuron fires on code identifiers—particularly element IDs or UI control names (e.g. “surveyScrollView,” “questionLayout,” “mpeEmpresa,” “imgList,” “slideShowContainer,” “timeline,” etc.).

    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
    gettyimages
    -1.35
    levis
    -1.31
    bermuda
    -1.29
    tvguide
    -1.27
     verhind
    -1.25
     by
    -1.16
    dsquared
    -1.16
    ambition
    -1.16
    aquarium
    -1.16
    rolex
    -1.16
    POSITIVE LOGITS
    Ｒ
    1.05
    Ţ
    1.05
    २
    1.03
    neiden
    1.02
     く
    1.02
    Ко
    1.00
    女性
    1.00
    كتب
    0.99
    )،
    0.99
    Mik
    0.98
    Activations Density 0.009%

    No Known Activations