© 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. 22-GEMMASCOPE-RES-131K
    7. 129760
    Prev
    Next
    INDEX
    Explanations

    The neuron detects version numbers (semantic-versioning strings) in package/dependency metadata.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Covid
    -1.40
     COVID
    -1.39
     covid
    -1.25
     TikTok
    -1.21
    covid
    -1.07
     pandemic
    -1.05
     macOS
    -1.05
    Covid
    -1.04
     androidx
    -1.02
    COVID
    -1.02
    POSITIVE LOGITS
     there
    1.12
     obed
    1.11
     xrange
    1.09
    кза
    1.09
     holand
    1.02
     stratégie
    1.00
    وزه
    0.99
    侪
    0.98
     unexpectedly
    0.98
     survie
    0.97
    Activations Density 0.003%

    No Known Activations