© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60583
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

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

    This neuron detects standalone numeric tokens (digits and small numbers) in the text.

    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
     Holdings
    -0.74
    currentThread
    -0.73
    Sister
    -0.70
    ится
    -0.70
     tá
    -0.70
     Chanel
    -0.69
    施工
    -0.68
     polar
    -0.67
     推
    -0.67
    PropTypes
    -0.66
    POSITIVE LOGITS
    ICLES
    0.72
     diventato
    0.68
    heartbeat
    0.67
    起点
    0.67
     Arki
    0.67
    ఉ
    0.66
    Heartbeat
    0.65
    fetchAll
    0.65
     (__
    0.64
     krishna
    0.64
    Activations Density 0.046%

    No Known Activations