© 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. 43568
    Prev
    Next
    INDEX
    Explanations

    Indian airports or brands

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

    The neuron strongly activates on numeric tokens (e.g. the floating‐point “length” numbers), i.e. it detects and highlights 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_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
     eenig
    -2.11
     indiví
    -1.95
     pán
    -1.91
    粜
    -1.91
     tunik
    -1.88
     rokok
    -1.80
    蚰
    -1.79
    鵟
    -1.79
     alho
    -1.78
     italie
    -1.77
    POSITIVE LOGITS
     all
    2.38
     in
    2.33
     There
    2.27
     These
    1.94
     are
    1.88
     They
    1.81
     at
    1.80
     всех
    1.76
     What
    1.75
     as
    1.74
    Activations Density 0.064%

    No Known Activations