© 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. 127990
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to numerical tokens—years, ages, dates, quantities, and other standalone numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
    を読む
    -1.16
    铤
    -1.13
    ,:);
    -1.11
     domésticos
    -1.09
    にしました
    -1.09
    anță
    -1.09
     bagay
    -1.06
     againſt
    -1.06
     Había
    -1.05
     ibang
    -1.05
    POSITIVE LOGITS
     vocale
    1.30
    马来西亚
    1.18
    泰国
    1.13
     municipale
    1.12
     tenues
    1.10
     gangen
    1.10
     civiles
    1.08
     schoenen
    1.06
    东京
    1.05
     maíz
    1.03
    Activations Density 0.251%

    No Known Activations