© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    images, scenes, and pictures

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

    The neuron activates on words referring to visual content—especially “scene,” “picture,” “image(s),” or “scenic.”

    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
    there
    -1.80
    िट
    -1.57
    鋅
    -1.55
    咴
    -1.52
     内衣
    -1.50
    ></
    -1.48
     It
    -1.48
    ísica
    -1.47
    Verwendung
    -1.47
    the
    -1.45
    POSITIVE LOGITS
    
    1.97
    ⑊
    1.89
     ряда
    1.88
    OURCES
    1.56
     warmen
    1.54
     totalmente
    1.49
    锝
    1.49
    龵
    1.48
     Caused
    1.48
     всем
    1.46
    Activations Density 0.007%

    No Known Activations