© 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. 34-GEMMASCOPE-RES-131K
    4. 37715
    Prev
    Next
    INDEX
    Explanations

    code and data sources

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

    The neuron fires on narrative prose mentioning people, their names, and what they’re doing (i.e. character-and-action narrative passages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Holstein
    -0.82
    Rozmiar
    -0.79
     pelic
    -0.78
     Blacklist
    -0.75
     đạo
    -0.75
    ünsche
    -0.72
    شيخ
    -0.72
     setImage
    -0.72
    calientes
    -0.71
    𝚈
    -0.71
    POSITIVE LOGITS
    Ud
    0.96
    aut
    0.91
     Oklahoma
    0.88
     Ud
    0.82
     tribes
    0.81
     decks
    0.79
     tribe
    0.78
     дода
    0.76
    tribe
    0.74
    Swing
    0.73
    Activations Density 0.002%

    No Known Activations