© 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. 60941
    Prev
    Next
    INDEX
    Explanations

    statement or proposal

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

    The main thing this neuron does is detect occurrences of the word “proposition.”

    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
     wth
    -2.72
    ⼥
    -2.66
     unſ
    -2.61
    with
    -2.61
    Zubereitung
    -2.61
     biß
    -2.44
     ratusan
    -2.39
     This
    -2.39
    1
    -2.36
     δύο
    -2.34
    POSITIVE LOGITS
    呖
    2.86
    𓄹
    2.80
    ܜ
    2.75
    焌
    2.73
    ൎ
    2.70
    曩
    2.58
    ჻
    2.55
    怍
    2.53
     shaky
    2.39
    𝄆
    2.39
    Activations Density 0.003%

    No Known Activations