© 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. 74640
    Prev
    Next
    INDEX
    Explanations

    github urls, file paths

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

    The neuron is specialized to spot GitHub “blob/master” URLs (i.e. repository file‐path segments indicating the master branch).

    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
     poté
    -2.00
    婊
    -1.98
     virksom
    -1.97
     produkter
    -1.84
     Conditioner
    -1.82
    鲧
    -1.80
     lefs
    -1.80
     befolk
    -1.79
    ción
    -1.73
    POSITIVE LOGITS
     While
    2.16
    こと
    2.13
    It
    2.11
    However
    2.09
     “(
    2.02
     eerie
    1.98
    This
    1.95
     Where
    1.93
     idyllic
    1.92
    這些
    1.91
    Activations Density 0.011%

    No Known Activations