© 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. 64634
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

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

    The neuron detects numeric values (digits or measurements) in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.86
     any
    -1.77
     both
    -1.66
     in
    -1.61
     on
    -1.59
     can
    -1.59
     make
    -1.55
     will
    -1.54
     more
    -1.54
     those
    -1.52
    POSITIVE LOGITS
     trám
    1.59
    盉
    1.38
    あー
    1.37
     rése
    1.30
    えっ
    1.27
    凄く
    1.26
    
    1.26
     interrom
    1.25
     unicórnio
    1.25
     enlever
    1.22
    Activations Density 0.025%

    No Known Activations