© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6972
    Prev
    Next
    INDEX
    Explanations

    opening punctuation or symbols

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

    The neuron is triggered by full‐width East Asian punctuation marks (e.g. Japanese corner brackets and parentheses).

    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
    0
    -3.16
    )
    -2.84
    _
    -2.77
    N
    -2.61
    2
    -2.59
    it
    -2.39
    1
    -2.36
     这个
    -2.34
    目前
    -2.33
    A
    -2.31
    POSITIVE LOGITS
    
    3.38
     apprécié
    2.67
    嬷
    2.63
    
    2.59
     reconnu
    2.58
     материалы
    2.56
     declaração
    2.56
     gerçekten
    2.55
     we
    2.53
    擼
    2.48
    Activations Density 0.000%

    No Known Activations