© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66519
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a space

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

    The neuron primarily detects numeric tokens (digit sequences), such as years, volume/page numbers, and other numbers in citations and bibliographic entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
        
    -1.63
     but
    -1.61
    </td>
    -1.54
     not
    -1.47
    -1.44
    要求
    -1.38
    थ
    -1.37
    \
    -1.33
    न
    -1.33
     "
    -1.31
    POSITIVE LOGITS
     tehd
    1.62
     możemy
    1.61
    塒
    1.49
     세트
    1.48
     કર
    1.47
     automatiques
    1.46
     esimerkiksi
    1.44
     Each
    1.44
     each
    1.43
    ӵ
    1.42
    Activations Density 0.010%
    No Known Activations