© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129266
    Prev
    Next
    INDEX
    Explanations

    biographical and genealogical information

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

    The neuron identifies genealogical or family‐history statements—mentions of relationships (married, child, ancestors, great‐great grandmother), vital events (born, died, buried), and other family‐record details.

    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
    ૉ
    -2.00
     TabLayout
    -1.91
     eenen
    -1.80
     ImageButton
    -1.77
    
    -1.70
    啭
    -1.66
     Arzne
    -1.66
     philippe
    -1.63
    𝜔
    -1.61
     SearchView
    -1.60
    POSITIVE LOGITS
     in
    1.75
     of
    1.66
     although
    1.47
    睑
    1.47
    conocimiento
    1.45
     Eigentü
    1.44
    普通の
    1.42
    savevideo
    1.37
     朝食
    1.36
    ଓ
    1.35
    Activations Density 0.258%

    No Known Activations