© 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. 32572
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    The neuron fires on multi-digit numeric tokens (especially three-digit-or-longer 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
    ]';
    -1.66
    👁
    -1.54
     '.$
    -1.41
    🙊
    -1.40
    órica
    -1.38
     amigas
    -1.38
     celebridades
    -1.38
    ;");
    -1.37
     msglen
    -1.36
     béisbol
    -1.36
    POSITIVE LOGITS
    2
    2.39
    5
    2.17
    8
    2.16
    7
    2.11
    4
    2.06
    1
    1.99
    6
    1.86
    3
    1.83
    了很多
    1.64
    9
    1.64
    Activations Density 0.021%

    No Known Activations