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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21790
    Prev
    Next
    INDEX
    Explanations

    French common nouns

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

    This neuron responds to isolated letter‐clusters (mostly two- or three-letter sequences and symbols) characteristic of garbled PDF/text-encoding artifacts.

    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
    dö
    -1.73
     what
    -1.59
     and
    -1.59
    </b>
    -1.57
     "...
    -1.56
     "[
    -1.55
     Kiedy
    -1.55
    něž
    -1.53
     ..."
    -1.53
    Bibliografie
    -1.52
    POSITIVE LOGITS
     of
    2.27
     habitudes
    1.77
    ”.
    1.76
     deuil
    1.75
     accessoire
    1.69
     automne
    1.65
     ovale
    1.65
     to
    1.63
    ”
    1.61
    许久
    1.60
    Activations Density 0.010%

    No Known Activations