© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101136
    Prev
    Next
    INDEX
    Explanations

    material design elements

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

    The neuron fires on mentions of Material Design libraries or components (e.g. “material,” “design,” and related Android/UI widget names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -1.64
     niedersachsen
    -1.64
    romas
    -1.52
    
    -1.50
     دیجیت
    -1.50
     高校
    -1.46
     zeitung
    -1.45
     Memoriam
    -1.41
    &.
    -1.41
    eping
    -1.39
    POSITIVE LOGITS
    Где
    1.45
     >
    1.38
     |
    1.27
     at
    1.25
    salms
    1.23
    国庆
    1.23
    ärer
    1.22
     change
    1.20
    Dota
    1.18
     Google
    1.16
    Activations Density 0.026%

    No Known Activations