© 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. 68693
    Prev
    Next
    INDEX
    Explanations

    quantities like two

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

    The neuron is looking for numeric quantity mentions (numbers in digits or words).

    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
    ﹶ
    -1.85
    他们的
    -1.63
    鉨
    -1.55
    臺北
    -1.51
    鸰
    -1.51
    Tapi
    -1.45
    蕷
    -1.44
    ellini
    -1.41
    ஂ
    -1.40
    他們的
    -1.38
    POSITIVE LOGITS
     メニュー
    1.45
     denselben
    1.41
    かどうか
    1.41
     jenen
    1.40
    ية
    1.40
    zupeł
    1.40
     almeno
    1.38
     juntamente
    1.38
     của
    1.37
     are
    1.35
    Activations Density 0.005%

    No Known Activations