© 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. 129857
    Prev
    Next
    INDEX
    Explanations

    numbered lists

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

    The neuron fires strongly on standalone numeric tokens used as list or section headings (e.g. “1,” “2,” “3,” 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_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
     not
    -2.42
     all
    -1.88
     other
    -1.79
     Despite
    -1.73
     in
    -1.72
     ALL
    -1.71
    .......
    -1.70
     aptly
    -1.69
    ........
    -1.69
     After
    -1.68
    POSITIVE LOGITS
     Dinas
    2.11
    鲩
    1.92
     maniere
    1.87
     praktische
    1.87
     délais
    1.82
    錾
    1.82
    蔸
    1.80
    豨
    1.78
    
    1.77
     giu
    1.74
    Activations Density 0.056%

    No Known Activations