© 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. 22-GEMMASCOPE-RES-131K
    4. 70562
    Prev
    Next
    INDEX
    Explanations

    journal citations and numbers

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

    The neuron activates on numeric tokens, especially multi‐digit numbers such as years, volume/pages, or reference identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     or
    -1.02
    циональный
    -0.98
     ‘
    -0.93
    {}",
    -0.91
    也是
    -0.90
    也
    -0.90
    ksjon
    -0.90
     Monday
    -0.87
    <i>
    -0.85
    <b>
    -0.85
    POSITIVE LOGITS
    没问题
    1.02
    我们是
    1.00
     Seizures
    0.99
    Дер
    0.95
    Дом
    0.93
    avocat
    0.93
    dáms
    0.93
     remis
    0.92
     볼
    0.91
     سامسون
    0.91
    Activations Density 0.003%

    No Known Activations