© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45535
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    The neuron strongly responds to standalone punctuation tokens (like commas and periods) and numeric digit tokens.

    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
    bosity
    -0.89
     COVID
    -0.88
    -0.88
     Biden
    -0.84
     ۱۴۰۰
    -0.78
     wichtigen
    -0.77
     zmniejs
    -0.77
     Covid
    -0.76
    bert
    -0.75
    Behavior
    -0.75
    POSITIVE LOGITS
     XXXVI
    0.94
    ²/
    0.92
     Huffington
    0.91
    ✝
    0.90
     تنظ
    0.90
     userService
    0.88
    ingredients
    0.88
     ®
    0.86
    croll
    0.86
     praktik
    0.85
    Activations Density 0.025%

    No Known Activations