© 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. 99324
    Prev
    Next
    INDEX
    Explanations

    but

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

    The neuron strongly fires on the Spanish conjunction “pero.”

    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
    at
    -4.47
     '
    -3.52
    m
    -3.27
    it
    -3.20
    an
    -3.20
    --
    -3.11
    i
    -3.11
    ('
    -3.09
    ar
    -3.00
    as
    -2.94
    POSITIVE LOGITS
    selben
    2.67
    つづく
    2.52
     Meilleures
    2.36
    Vlast
    2.31
    lüğü
    2.17
    魮
    2.17
    ーーーー
    2.16
    錼
    2.14
    Another
    2.14
    vantaged
    2.13
    Activations Density 0.001%

    No Known Activations