© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59814
    Prev
    Next
    INDEX
    Explanations

    writing and rhetoric

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

    The neuron fires on document metadata labels and section headings (e.g. “Abstract,” “Chapter,” “Location,” “Type of Presentation,” etc.).

    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
     Philos
    -0.88
    爰
    -0.84
    NEYS
    -0.75
    手法
    -0.75
    ències
    -0.75
    pak
    -0.75
     ユニ
    -0.74
     Seligman
    -0.73
    manı
    -0.73
     defire
    -0.73
    POSITIVE LOGITS
     rhetorical
    1.67
     rhetor
    1.52
    rhe
    1.36
    Rhe
    1.27
     Rhetor
    1.27
     Writing
    1.13
     writing
    1.09
    Composition
    1.09
    Writing
    1.05
     composing
    1.04
    Activations Density 0.029%

    No Known Activations