© 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. 34-GEMMASCOPE-RES-131K
    7. 262
    Prev
    Next
    INDEX
    Explanations

    solid border colors

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

    The neuron fires on CSS property‐value syntax—especially numeric measurements (like “1px”) and punctuation (colons, semicolons) in style declarations (e.g. border definitions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    really
    -0.81
     飲み
    -0.81
    未
    -0.79
    melte
    -0.79
    衣服
    -0.75
     valutazione
    -0.75
    呵
    -0.74
    CÓ
    -0.74
    JsonInclude
    -0.72
     Bunt
    -0.71
    POSITIVE LOGITS
     black
    1.88
     Black
    1.46
     red
    1.41
    black
    1.38
    BLACK
    1.30
    Black
    1.27
     BLACK
    1.25
     pink
    1.10
     blue
    1.07
    黒
    1.06
    Activations Density 0.013%

    No Known Activations