© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99641
    Prev
    Next
    INDEX
    Explanations

    Japanese publications and proceedings

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

    The neuron selectively activates on multi‐digit numerals (e.g. years, issue numbers, counts) wherever they appear in the text.

    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
     Europeans
    -0.98
     European
    -0.89
     Евро
    -0.88
    european
    -0.85
    Hao
    -0.81
     tilgjenge
    -0.80
    acap
    -0.79
    槇
    -0.79
     Worldwide
    -0.79
     Poker
    -0.79
    POSITIVE LOGITS
    〈
    1.03
    學習
    0.85
    Aktu
    0.84
    lastIndex
    0.83
     Enkel
    0.81
    assertIn
    0.80
    Ikus
    0.78
     speciali
    0.78
     altra
    0.77
    ミ
    0.77
    Activations Density 0.008%

    No Known Activations