© 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. 72067
    Prev
    Next
    INDEX
    Explanations

    any followed by noun

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

    The neuron fires on tokens containing the letter sequence “any” (e.g. any, anyone, anybody, etc.).

    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
     flexível
    -1.69
     decorativa
    -1.60
     régal
    -1.57
    覿
    -1.55
     學
    -1.54
     桥
    -1.51
    夀
    -1.50
    مدل
    -1.49
    ATION
    -1.48
    েকে
    -1.48
    POSITIVE LOGITS
    ↵↵
    2.08
     not
    1.69
     if
    1.66
     for
    1.62
     they
    1.62
     what
    1.50
     iets
    1.45
     where
    1.43
    COT
    1.42
     For
    1.41
    Activations Density 0.007%

    No Known Activations