© 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. 84445
    Prev
    Next
    INDEX
    Explanations

    URLs with `://`

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

    The neuron fires on non‐natural-language or markup tokens such as URL schemes (e.g. “https”) and full-width punctuation (e.g. “（”).

    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
     "
    -2.11
    IANGLES
    -1.92
     it
    -1.90
     '
    -1.88
     all
    -1.87
     this
    -1.85
     he
    -1.84
     in
    -1.80
     so
    -1.77
     to
    -1.71
    POSITIVE LOGITS
     maría
    1.82
    婳
    1.78
     hansen
    1.77
     ghiaccio
    1.75
    是一個
    1.74
     つの
    1.73
     hvil
    1.73
    峤
    1.73
     réfrig
    1.72
    -¡
    1.70
    Activations Density 0.001%

    No Known Activations