© 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. 68700
    Prev
    Next
    INDEX
    Explanations

    let go, slip, run, fall

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

    The neuron fires strongly on occurrences of the verb “go.”

    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
     réinitial
    -1.77
     denkt
    -1.76
     rafra
    -1.70
     etre
    -1.66
     misterioso
    -1.64
     perpé
    -1.63
     广告
    -1.61
     Diſ
    -1.60
    ﺢ
    -1.59
     rafraî
    -1.57
    POSITIVE LOGITS
    2
    2.70
    3
    2.69
    ↵
    2.53
    ?
    2.25
     in
    2.20
    )
    2.14
    5
    2.13
    4
    2.13
     if
    2.09
    1
    2.08
    Activations Density 0.006%

    No Known Activations