© 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. 365
    Prev
    Next
    INDEX
    Explanations

    URLs, names, and numbers

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

    The neuron detects numeric tokens or digit‐containing sequences (dates, years, DOIs, reference numbers, 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_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
    Ѕ
    -0.98
     ของ
    -0.97
    </h1>
    -0.94
    {
    
    -0.94
    :「
    -0.86
    آن
    -0.85
    ₡
    -0.84
    関する
    -0.83
     ngoài
    -0.82
     良い
    -0.82
    POSITIVE LOGITS
    rillation
    1.13
    fordshire
    0.93
     more
    0.93
     https
    0.92
     less
    0.90
    ]]>
    0.89
    راءة
    0.89
    <eos>
    0.88
    neous
    0.84
    urization
    0.83
    Activations Density 0.079%

    No Known Activations