© 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. 10-GEMMASCOPE-RES-131K
    7. 38481
    Prev
    Next
    INDEX
    Explanations

    dues, toes, or Honours

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

    This neuron activates on tokens that are numeric values or amounts (i.e. sequences of digits, including integers and decimals).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0
    -2.88
    1
    -2.55
    k
    -2.44
     ‘’
    -2.27
    他就
    -2.23
    d
    -2.20
    ஂ
    -2.17
     BRARY
    -2.11
    </td>
    -2.06
     {
    -2.05
    POSITIVE LOGITS
    </strong>
    2.67
    鼇
    2.13
    𞤢
    1.98
    
    1.95
     迷你
    1.93
    urlopen
    1.91
    込んだ
    1.91
    ра
    1.90
    咐
    1.89
     Они
    1.88
    Activations Density 0.005%

    No Known Activations