© 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. 10-GEMMASCOPE-RES-131K
    7. 41446
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and quantities

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

    The neuron is detecting hyphen or dash characters in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -2.33
    other
    -1.71
    to
    -1.60
    on
    -1.55
     haki
    -1.51
     Other
    -1.48
     What
    -1.47
    product
    -1.46
    </h1>
    -1.43
     Now
    -1.42
    POSITIVE LOGITS
     zelfs
    2.08
     этого
    1.84
     была
    1.68
     niektórych
    1.60
     této
    1.55
    ӣ
    1.52
    Société
    1.47
    行
    1.45
    Magyar
    1.45
    製の
    1.45
    Activations Density 0.037%

    No Known Activations