© 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. 34-GEMMASCOPE-RES-131K
    7. 3622
    Prev
    Next
    INDEX
    Explanations

    gum and gummi-related contexts

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

    This neuron activates on the letter sequence “gum,” i.e. words containing or beginning with “gum.”

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     колен
    -0.81
    estia
    -0.77
     tons
    -0.77
    飼い
    -0.74
    นวน
    -0.74
    skjaer
    -0.72
    ivant
    -0.72
    する場合
    -0.72
    lainen
    -0.71
     cream
    -0.71
    POSITIVE LOGITS
    Gum
    1.20
     Gum
    1.19
    gum
    1.08
     arabic
    1.07
     Arabic
    0.88
     gum
    0.85
    boots
    0.85
    mbalikan
    0.85
     ול
    0.82
    Arabic
    0.81
    Activations Density 0.018%

    No Known Activations