© 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. 86810
    Prev
    Next
    INDEX
    Explanations

    instantiating view controllers

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

    The neuron is primarily triggered by numeric tokens (sequences of digits) 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
    ]=="
    -0.75
     scenic
    -0.75
    融资
    -0.73
     অন
    -0.71
    셨
    -0.70
    さんを
    -0.69
    urement
    -0.69
    zoom
    -0.69
    ingo
    -0.69
     notation
    -0.69
    POSITIVE LOGITS
     Staging
    0.69
     Grizzlies
    0.66
     PRACTICES
    0.66
    静
    0.66
     Grading
    0.65
     Districts
    0.64
     Softball
    0.64
     hiv
    0.63
     Balkans
    0.63
    抽象
    0.61
    Activations Density 0.063%

    No Known Activations