© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70817
    Prev
    Next
    INDEX
    Explanations

    school performance testing and results

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

    The neuron detects numeric tokens and numerical data (years, counts, percentages, and other figures).

    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
    ׇ
    -2.03
     ویتامین
    -1.46
     النبات
    -1.42
     campesinos
    -1.34
     begge
    -1.34
     иллюстрация
    -1.32
    丨
    -1.32
     drinken
    -1.31
    ଶ
    -1.29
    rounder
    -1.28
    POSITIVE LOGITS
     performance
    1.84
     school
    1.84
     children
    1.73
     teacher
    1.60
     across
    1.59
    ּוֹ
    1.57
     year
    1.55
    ִּ
    1.51
     improvement
    1.48
     district
    1.40
    Activations Density 0.045%

    No Known Activations