© 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. 79783
    Prev
    Next
    INDEX
    Explanations

    comma followed by conjunction

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

    The neuron primarily activates on comma punctuation, marking clause or phrase boundaries.

    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
     there
    -1.86
     we
    -1.62
     for
    -1.32
     these
    -1.30
     from
    -1.30
     some
    -1.25
     that
    -1.20
     (
    -1.20
     where
    -1.15
     you
    -1.12
    POSITIVE LOGITS
    uteurs
    1.30
     "
    1.25
     grec
    1.20
     zijne
    1.19
     evenement
    1.17
    mless
    1.16
    
    1.14
     pesar
    1.13
    venir
    1.12
     klin
    1.11
    Activations Density 0.020%

    No Known Activations