© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84473
    Prev
    Next
    INDEX
    Explanations

    names or places

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

    The neuron predominantly activates on proper names and place 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
     cuyos
    -1.47
     simplemente
    -1.43
     L
    -1.40
     by
    -1.40
    óval
    -1.31
     if
    -1.30
     cuyo
    -1.30
    ar
    -1.30
     whose
    -1.29
    andangan
    -1.29
    POSITIVE LOGITS
     itſelf
    1.91
     ſy
    1.83
    摃
    1.76
    鹟
    1.71
     guir
    1.69
     bebes
    1.67
     eſſ
    1.67
     strategi
    1.67
     broche
    1.66
     fras
    1.66
    Activations Density 0.003%

    No Known Activations