© 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. 34-GEMMASCOPE-RES-131K
    7. 99229
    Prev
    Next
    INDEX
    Explanations

    licenses and copyright notices

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

    The main thing this neuron does is detect numeric tokens (numbers and version or license 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
     others
    -0.79
    вропей
    -0.75
    ₁,
    -0.68
    ٢
    -0.67
    泉
    -0.66
    搜索
    -0.66
     screwed
    -0.65
    Souza
    -0.65
    gat
    -0.64
    moon
    -0.64
    POSITIVE LOGITS
    Lng
    0.84
     communiquer
    0.76
    延伸閱讀
    0.73
     offici
    0.71
     Rei
    0.71
    utex
    0.70
     Carpenter
    0.69
     regardé
    0.68
    Carpenter
    0.68
     अंत
    0.68
    Activations Density 0.031%

    No Known Activations