© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95511
    Prev
    Next
    INDEX
    Explanations

    ages and grades of children

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

    The neuron activates on numeric tokens and expressions—especially ages, grades, years, and other numbers.

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

    No Comments

    Negative Logits
     college
    -1.33
    ’
    -1.19
    College
    -1.16
    -
    -1.12
     College
    -1.12
     colleges
    -1.11
    college
    -1.11
    —
    -1.09
     of
    -1.03
    Colle
    -1.02
    POSITIVE LOGITS
     děti
    1.73
     children
    1.58
    苙
    1.29
    <bos>
    1.28
    children
    1.27
    Schriften
    1.23
    hetti
    1.22
     Ở
    1.20
    Gep
    1.19
     ヌード
    1.19
    Activations Density 0.059%

    No Known Activations