© 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. 38622
    Prev
    Next
    INDEX
    Explanations

    year anniversary plans

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

    The neuron is primarily triggered by colon characters (":"), marking punctuation that introduces lists, subtitles, or explanatory clauses.

    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
     السياس
    -2.36
     or
    -1.95
    كيف
    -1.80
     October
    -1.80
    𝒙
    -1.78
     TWO
    -1.76
     three
    -1.75
     after
    -1.74
     November
    -1.74
     two
    -1.73
    POSITIVE LOGITS
     abraço
    2.36
     chapéu
    2.20
     beijo
    2.17
     herói
    2.17
     relógio
    2.08
     braço
    2.06
     设计
    1.98
    
    1.98
     semelh
    1.94
     قوات
    1.93
    Activations Density 1.112%

    No Known Activations