© 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. 10-GEMMASCOPE-RES-131K
    7. 1704
    Prev
    Next
    INDEX
    Explanations

    UI container elements

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

    The neuron fires on HTML element tags that specify CSS styling—i.e. tags with class or style attributes (especially class names containing underscores or dashes).

    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
    鏨
    -1.67
    issipp
    -1.51
     forbindelse
    -1.47
    htë
    -1.44
    жела
    -1.40
    銠
    -1.40
    tedrale
    -1.39
    珢
    -1.38
     mutta
    -1.38
     frantically
    -1.37
    POSITIVE LOGITS
    います
    1.38
    ,
    1.35
    多く
    1.28
     us
    1.25
    おわりに
    1.21
    うちに
    1.20
    門口
    1.20
     praktische
    1.18
     mittlere
    1.15
     anunciar
    1.13
    Activations Density 0.016%

    No Known Activations