© 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. 64286
    Prev
    Next
    INDEX
    Explanations

    words in parentheses

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

    The main thing this neuron does is detect standalone multi-digit 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
     (
    -1.63
     There
    -1.54
     evidently
    -1.40
    -1.36
     it
    -1.32
     in
    -1.32
     They
    -1.30
     As
    -1.28
     Because
    -1.27
    》。
    -1.25
    POSITIVE LOGITS
    ఽ
    1.42
     améli
    1.36
     erhi
    1.35
    liana
    1.33
    SOME
    1.33
     enfermos
    1.32
    ματα
    1.31
     ジップ
    1.28
    could
    1.27
     embaraz
    1.27
    Activations Density 0.022%

    No Known Activations