© 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. 22-GEMMASCOPE-RES-131K
    7. 24992
    Prev
    Next
    INDEX
    Explanations

    potential or possibility of outcomes

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

    This neuron fires on the word “potential” (especially in phrases like “has the potential to”) indicating expressions of possibility or potential outcomes.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     poursuivre
    -1.37
     často
    -1.36
    鞴
    -1.32
     réfléchir
    -1.30
     naer
    -1.30
     épaules
    -1.29
     westfalen
    -1.28
    塒
    -1.28
     réparer
    -1.27
     soos
    -1.27
    POSITIVE LOGITS
     even
    1.89
     sogar
    1.75
     could
    1.66
     potentially
    1.62
     if
    1.62
     jopa
    1.58
     very
    1.55
     also
    1.50
     possibly
    1.49
     may
    1.42
    Activations Density 0.033%

    No Known Activations