© 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. 45401
    Prev
    Next
    INDEX
    Explanations

    quotation marks and names

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

    The neuron fires on non-standard punctuation or typographic symbols (long dashes, bullets/arrows, heavy quote marks, etc.).

    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
    1
    -3.58
    3
    -3.23
    0
    -3.16
    5
    -3.14
     Using
    -3.13
     Surprisingly
    -3.11
    2
    -3.09
     Ironically
    -3.02
     Usually
    -2.98
    For
    -2.91
    POSITIVE LOGITS
    圌
    3.19
    苤
    3.08
     และ
    3.03
    蓠
    3.00
    🫅
    2.97
     zoude
    2.94
     dando
    2.78
    糨
    2.72
    姽
    2.72
    
    2.72
    Activations Density 0.003%

    No Known Activations