© 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. 16740
    Prev
    Next
    INDEX
    Explanations

    a/an/the followed by technical terms

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

    The neuron activates on numeric tokens (numbers).

    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
     disponibilités
    -1.55
    €”
    -1.52
     démission
    -1.48
    킁
    -1.46
     dwóch
    -1.45
     décider
    -1.44
    ufficient
    -1.41
     Tienen
    -1.41
     músicos
    -1.40
     Qualquer
    -1.40
    POSITIVE LOGITS
     for
    1.50
     only
    1.49
    d
    1.41
     in
    1.39
    w
    1.37
    ar
    1.36
     with
    1.34
    k
    1.32
    le
    1.31
    i
    1.30
    Activations Density 0.002%

    No Known Activations