© 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. 22-GEMMASCOPE-RES-131K
    4. 93
    Prev
    Next
    INDEX
    Explanations

    code syntax, non-English words

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

    The neuron is activated by numeric tokens (e.g. line numbers, row/column values, or other numbers) in the document.

    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
     that
    -1.11
    makebox
    -1.05
     because
    -0.98
     récompense
    -0.94
     damaligen
    -0.93
     牛奶
    -0.92
    
    -0.90
     Grüßen
    -0.90
    それにしても
    -0.90
     بسیار
    -0.89
    POSITIVE LOGITS
    offsetof
    0.93
    RequestQueue
    0.89
     மற்ற
    0.89
     teilnehmen
    0.88
     niveaux
    0.88
    IANS
    0.86
    msgTypes
    0.86
    НОЕ
    0.86
     pomeriggio
    0.84
    ᴋ
    0.83
    Activations Density 0.002%

    No Known Activations