© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29930
    Prev
    Next
    INDEX
    Explanations

    proper names and places

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

    The neuron strongly activates on four‐letter subword chunks at the beginnings of proper names (e.g. “Kog,” “Nog,” “Jog,” “vog,” “Yog,” “Co gh,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     pou
    -0.81
    ங
    -0.73
     Воз
    -0.71
     pare
    -0.71
     Luk
    -0.71
    Buildable
    -0.70
    卧室
    -0.70
    collapsed
    -0.70
    Western
    -0.69
     पढ़
    -0.68
    POSITIVE LOGITS
    Gobierno
    0.81
     DFS
    0.79
    uing
    0.79
     thermometers
    0.79
     uc
    0.77
    amaged
    0.75
    Consejo
    0.74
    ⠹
    0.73
    requestId
    0.72
     slicer
    0.71
    Activations Density 0.031%

    No Known Activations