© 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. 67892
    Prev
    Next
    INDEX
    Explanations

    list separators

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

    The neuron is detecting specialized, domain-specific technical or formal jargon terms.

    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
    gencies
    -1.05
    就
    -0.99
    代表
    -0.99
     только
    -0.96
    seudo
    -0.96
    <bos>
    -0.96
    arcas
    -0.91
    将
    -0.91
     духовке
    -0.90
    ɦ
    -0.88
    POSITIVE LOGITS
    nuevos
    1.09
    diferentes
    1.08
     тях
    1.08
    calidad
    1.02
    termilk
    1.02
    Eles
    1.02
     them
    1.00
    暱
    0.99
    those
    0.99
     والتي
    0.98
    Activations Density 0.084%

    No Known Activations