© 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. 6999
    Prev
    Next
    INDEX
    Explanations

    subtypes of subtypes

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

    The neuron is sensitive to numeric tokens (whole numbers and decimals).

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

    No Comments

    Negative Logits
    wiście
    -2.75
     terwijl
    -2.36
     zodat
    -2.33
    い
    -2.28
    acuation
    -2.20
    鸲
    -2.19
     omdat
    -2.19
    嗩
    -2.17
    儈
    -2.17
     تقوم
    -2.14
    POSITIVE LOGITS
    ጵ
    2.63
    м
    2.56
    何度も
    2.53
    のは
    2.52
    to
    2.47
    何度
    2.33
    u
    2.33
    蘗
    2.31
    運び
    2.27
    ية
    2.22
    Activations Density 0.007%

    No Known Activations