© 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. 34-GEMMASCOPE-RES-131K
    7. 1640
    Prev
    Next
    INDEX
    Explanations

    names starting with By

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

    The neuron fires strongly on pieces of proper names (e.g. personal names, bylines, place names) and so is detecting fragments of named entities.

    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
     aufgenommen
    -0.73
     Prefer
    -0.73
     thận
    -0.71
    ரிய
    -0.71
    独
    -0.68
    tré
    -0.67
     coords
    -0.67
     trava
    -0.67
    casas
    -0.67
     doppelt
    -0.66
    POSITIVE LOGITS
     Byrd
    0.89
    jmniej
    0.88
     BY
    0.87
     By
    0.86
    ágos
    0.85
     claws
    0.83
     byt
    0.82
    ugan
    0.81
    byg
    0.81
    bygg
    0.80
    Activations Density 0.028%

    No Known Activations