© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92698
    Prev
    Next
    INDEX
    Explanations

    searching for xml, questions, or scientific terms

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

    The neuron activates on numeric sports scorelines, especially patterns like “number to number” (e.g., “4 to 2”).

    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
    擬
    -0.84
     Lacy
    -0.82
     synagogue
    -0.81
     роман
    -0.79
    levelse
    -0.78
    enfance
    -0.77
    bantu
    -0.76
    هدف
    -0.75
     különböz
    -0.75
    retanto
    -0.75
    POSITIVE LOGITS
    יז
    0.75
     six
    0.74
     score
    0.73
     cháu
    0.71
    PostId
    0.70
     TikTok
    0.69
    6
    0.68
    くな
    0.68
    %``
    0.67
     Carmen
    0.66
    Activations Density 0.012%

    No Known Activations