© 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. 90031
    Prev
    Next
    INDEX
    Explanations

    business and technical dates

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

    The neuron fires on tokens that are part of document headings or titles—particularly all-caps names, stock tickers, section headers, and other headline‐style text.

    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
    假的
    -0.85
    手紙
    -0.81
    𝟚
    -0.80
     inmediatamente
    -0.78
    グラ
    -0.77
    vlád
    -0.75
    困难
    -0.73
     rápidamente
    -0.72
     temperatures
    -0.72
     ditentukan
    -0.72
    POSITIVE LOGITS
    ailles
    0.81
    ísica
    0.81
     scissor
    0.81
     диван
    0.78
     Zack
    0.78
     Guilherme
    0.77
     Raster
    0.77
     Méndez
    0.76
    žil
    0.76
     bedre
    0.76
    Activations Density 0.001%

    No Known Activations