© 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. 68616
    Prev
    Next
    INDEX
    Explanations

    Saint names and places

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

    The neuron fires on “St”/“Saint” tokens and related church or dedication names (e.g. “St Paul,” “St Mary,” “Sacred Heart”)—in other words, it detects saint-based place or church names.

    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
    </strong>
    -1.70
     También
    -1.51
     The
    -1.47
     paisagem
    -1.46
     Große
    -1.44
    調味料
    -1.43
    .”
    -1.41
     universidad
    -1.35
    懨
    -1.32
    visiae
    -1.30
    POSITIVE LOGITS
     спросил
    1.55
    Bigr
    1.50
    BindView
    1.39
    thanes
    1.33
    vė
    1.33
    つける
    1.33
    rdoba
    1.32
    涣
    1.32
     afirma
    1.32
     who
    1.32
    Activations Density 0.020%

    No Known Activations