© 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. 10-GEMMASCOPE-RES-131K
    4. 104467
    Prev
    Next
    INDEX
    Explanations

    Name and author

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

    This neuron detects parenthesized occupational or role labels (e.g. “(author)”, “(judge)”, “(writer)”) following person names.

    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
     because
    -1.88
    ↵↵
    -1.77
     \
    -1.59
     an
    -1.57
     these
    -1.54
     These
    -1.34
    These
    -1.30
    1
    -1.30
    Being
    -1.20
     if
    -1.20
    POSITIVE LOGITS
     ujedno
    1.59
     سيكون
    1.48
    使って
    1.43
     considérer
    1.38
     Спасибо
    1.36
    cribir
    1.35
    enablog
    1.35
    เลือก
    1.30
     Tất
    1.30
    Viitteet
    1.30
    Activations Density 0.009%

    No Known Activations