© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30674
    Prev
    Next
    INDEX
    Explanations

    Google URLs and services

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

    The neuron strongly activates on numeric and digit‐containing tokens (e.g. years, dates, times, and other numbers).

    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
    setStyleSheet
    -0.75
     cường
    -0.75
    🛡
    -0.75
    iphone
    -0.71
    getRow
    -0.69
    🐾
    -0.69
    ڭ
    -0.69
     Candle
    -0.68
    Ż
    -0.68
     Sect
    -0.68
    POSITIVE LOGITS
     Google
    2.08
    Google
    2.06
    google
    1.67
     google
    1.48
     GOOGLE
    1.47
    GOOGLE
    1.38
    谷歌
    1.18
     goog
    1.15
     Goo
    1.04
    グー
    1.01
    Activations Density 0.103%

    No Known Activations