© 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. 10-GEMMASCOPE-RES-131K
    7. 83804
    Prev
    Next
    INDEX
    Explanations

    described as or shown to

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

    This neuron detects passive‐voice perfect constructions used to report findings, e.g. phrases like “has been shown,” “has been described,” or “have been suggested.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    j
    -1.62
    {
    -1.59
    c
    -1.57
    to
    -1.45
    ns
    -1.45
    z
    -1.40
    ner
    -1.40
    na
    -1.39
    my
    -1.33
    ul
    -1.31
    POSITIVE LOGITS
     but
    1.63
     controladores
    1.60
    adrez
    1.59
     également
    1.56
     Consejos
    1.53
    淠
    1.53
    aussi
    1.52
     also
    1.48
     necesariamente
    1.48
     xadrez
    1.48
    Activations Density 0.164%

    No Known Activations