© 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. 22-GEMMASCOPE-RES-131K
    7. 68703
    Prev
    Next
    INDEX
    Explanations

    life, society, and culture

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

    The neuron detects high-register academic jargon—abstract nouns and concepts (e.g. disputation, intellectual, manifestations, levels, society) typical of scholarly discourse.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     you
    -1.47
    还有一个
    -1.30
    égal
    -1.27
     provenant
    -1.25
     then
    -1.24
     fortfarande
    -1.23
     tiež
    -1.22
     najdete
    -1.22
    tissimi
    -1.20
     conservación
    -1.17
    POSITIVE LOGITS
    を選択します
    1.29
    istani
    1.29
     coreano
    1.27
    🥽
    1.27
     variedades
    1.23
     obnoxious
    1.21
     ventajas
    1.20
     ondas
    1.19
    匾
    1.18
    letics
    1.17
    Activations Density 0.100%

    No Known Activations