© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28158
    Prev
    Next
    INDEX
    Explanations

    html/code elements and foreign words

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

    The neuron responds strongly to tokens that occur in module or package names in import/require statements (i.e. npm dependency identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     on
    -1.88
     at
    -1.87
     with
    -1.74
     in
    -1.74
     all
    -1.72
     because
    -1.61
     to
    -1.53
     without
    -1.50
     have
    -1.46
     from
    -1.45
    POSITIVE LOGITS
     faciliter
    1.45
     maniere
    1.44
     publier
    1.44
     indiquer
    1.42
     áng
    1.40
     régal
    1.39
     participer
    1.38
     coûts
    1.34
     intelligente
    1.32
    ほとん
    1.30
    Activations Density 0.002%

    No Known Activations