© 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. 10-GEMMASCOPE-RES-131K
    7. 44107
    Prev
    Next
    INDEX
    Explanations

    URLs, DOIs, and citations

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

    The neuron fires on numeric tokens—especially digit sequences in DOIs and URLs.

    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
    StoryboardSegue
    -1.63
    WAUKEE
    -1.53
     largeur
    -1.46
    APOLIS
    -1.37
     []:
    -1.35
    ンの
    -1.32
    Those
    -1.30
    WebpackPlugin
    -1.30
    mathrm
    -1.28
    izacja
    -1.28
    POSITIVE LOGITS
     it
    2.11
     the
    1.79
     with
    1.39
     públicas
    1.38
    かっこ
    1.36
    apparition
    1.34
     måte
    1.34
     hvilke
    1.30
     its
    1.30
    カッコ
    1.29
    Activations Density 0.004%

    No Known Activations