© 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. 84218
    Prev
    Next
    INDEX
    Explanations

    but, and, or

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

    The neuron is highly sensitive to comma tokens, essentially detecting commas (i.e. clause-separating punctuation).

    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
    そのため
    -1.44
    zyć
    -1.44
    ↵
    -1.34
     Spisak
    -1.34
     alfo
    -1.31
     ویکی
    -1.30
     Istri
    -1.29
     Grüßen
    -1.29
    chuhe
    -1.28
     ambiti
    -1.28
    POSITIVE LOGITS
     or
    2.53
     and
    2.03
     if
    1.67
     that
    1.52
     in
    1.51
    panasonic
    1.49
     jeśli
    1.44
     albeit
    1.41
     needed
    1.38
     which
    1.38
    Activations Density 0.090%

    No Known Activations