© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101198
    Prev
    Next
    INDEX
    Explanations

    emojis, context markers

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

    The neuron detects pictographic Unicode symbols (emojis, flags, and similar non-alphanumeric icons).

    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
    </em>
    -2.13
    </h2>
    -1.80
    ).
    -1.78
    瑧
    -1.70
     Honestly
    -1.64
    焄
    -1.60
    Ivoire
    -1.60
     冷
    -1.56
     ل
    -1.52
    Not
    -1.50
    POSITIVE LOGITS
    也想
    2.06
    鬭
    2.02
    ೣ
    1.96
    鹛
    1.85
    铩
    1.82
     oorspron
    1.80
    嘖
    1.80
    枼
    1.79
    
    1.79
     foremost
    1.78
    Activations Density 0.001%

    No Known Activations