© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67302
    Prev
    Next
    INDEX
    Explanations

    class definitions

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

    The neuron is looking for file‐level boilerplate comment headers (e.g. copyright and license blocks) in source code.

    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
     Nikon
    -1.08
    IPV
    -1.00
     Barangay
    -0.98
     Pinterest
    -0.98
     VW
    -0.98
     chirurgie
    -0.98
     cliché
    -0.97
    Ū
    -0.97
     Linkedin
    -0.97
    蓠
    -0.97
    POSITIVE LOGITS
     even
    1.42
     what
    1.41
     using
    1.25
     only
    1.23
     there
    1.23
     not
    1.22
     everything
    1.19
     There
    1.17
     after
    1.15
     these
    1.14
    Activations Density 0.582%

    No Known Activations