© 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. 32856
    Prev
    Next
    INDEX
    Explanations

    counting many things

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

    The neuron fires strongly on numeric quantity tokens, i.e. digits or numbers specifying counts or measures.

    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
     to
    -1.16
     when
    -1.14
     first
    -1.11
     did
    -1.09
    訥
    -1.08
    cornerRadius
    -1.03
     некоторых
    -1.02
     einiger
    -1.02
     before
    -1.00
    ştır
    -0.98
    POSITIVE LOGITS
     you
    1.62
     akár
    1.49
     your
    1.49
     belieb
    1.38
     unlimited
    1.27
     Inſ
    1.27
     egyszer
    1.19
    enzen
    1.18
     député
    1.17
    byes
    1.16
    Activations Density 0.058%

    No Known Activations