© 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. 70318
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions

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

    This neuron fires on the hyphen (dash) token in 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
    也
    -1.86
    <td>
    -1.55
     リバー
    -1.53
    咘
    -1.53
    ;%%
    -1.52
    ikuti
    -1.49
    还
    -1.47
    끽
    -1.45
    ischof
    -1.44
     steuer
    -1.44
    POSITIVE LOGITS
    ’
    1.70
     because
    1.66
    様が
    1.58
     ventured
    1.52
     نمی
    1.49
    了些
    1.48
    姿态
    1.47
    了自己
    1.44
    ).
    1.42
    id
    1.41
    Activations Density 0.067%

    No Known Activations