© 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. 93193
    Prev
    Next
    INDEX
    Explanations

    technical nouns followed by punctuation

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

    The neuron activates on technical nouns naming software components or configuration elements.

    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
     pirata
    -1.13
     vanden
    -1.01
     maestra
    -1.00
     prêtre
    -0.99
     kuitenkin
    -0.96
     circonstances
    -0.96
     occuper
    -0.96
     musées
    -0.96
    hopefully
    -0.95
     bénévol
    -0.95
    POSITIVE LOGITS
     nor
    2.45
     because
    1.84
     sondern
    1.76
     anymore
    1.73
     until
    1.52
    而是
    1.41
     enough
    1.30
     due
    1.29
     resulting
    1.28
    nor
    1.24
    Activations Density 0.135%

    No Known Activations