© 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. 22815
    Prev
    Next
    INDEX
    Explanations

    words ending in ZIONE di

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

    The neuron fires on standalone label‐style tokens that head sections or metadata fields (e.g. “Sezione,” “invoice,” “attorneys,” “collections”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    s
    -3.44
    埽
    -3.38
    p
    -3.23
    felizmente
    -2.98
    ’
    -2.97
     that
    -2.88
    ѣмъ
    -2.84
    䛗
    -2.83
    wijl
    -2.81
    c
    -2.81
    POSITIVE LOGITS
     
    2.78
    In
    2.47
     важ
    2.39
     Commonly
    2.39
    ～～
    2.39
    
    2.38
     Primarily
    2.38
    もちろん
    2.33
     pendekatan
    2.33
    誊
    2.30
    Activations Density 0.029%

    No Known Activations