© 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. 10-GEMMASCOPE-RES-131K
    4. 105937
    Prev
    Next
    INDEX
    Explanations

    directions and regions

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

    This neuron detects hyphens (the dash character) in compounds or titles.

    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
     empê
    -1.52
     évalu
    -1.49
     normalerweise
    -1.43
    趿
    -1.43
    zsef
    -1.42
    tagext
    -1.40
    莇
    -1.40
    祤
    -1.38
     rédig
    -1.38
     कई
    -1.38
    POSITIVE LOGITS
    龵
    1.76
     that
    1.63
    栢
    1.55
    ୈ
    1.49
    Only
    1.48
    bernador
    1.44
    }\]
    1.41
    GRAFIA
    1.41
    がて
    1.39
    You
    1.38
    Activations Density 0.020%

    No Known Activations