© 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. 72831
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    The neuron strongly activates on capitalized proper-noun tokens (especially personal names).

    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
    ஂ
    -2.92
    \
    -2.56
    on
    -2.45
    
    -2.36
    同上
    -2.31
    螓
    -2.30
    {
    -2.28
    With
    -2.25
    In
    -2.20
     モード
    -2.19
    POSITIVE LOGITS
    屺
    2.73
     kurzem
    2.72
    婼
    2.66
     émotions
    2.64
    泚
    2.61
     disponibilités
    2.47
     conhece
    2.45
     respald
    2.44
    澡
    2.41
    
    2.41
    Activations Density 0.004%

    No Known Activations