© 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. 34-GEMMASCOPE-RES-131K
    4. 54183
    Prev
    Next
    INDEX
    Explanations

    educational levels and questions

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

    The neuron detects mentions of educational grade or curriculum level labels (e.g. “Grade 9-1,” “GCSE,” “KS3,” “Lower Secondary,” “Higher Level,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     senior
    -1.04
    senior
    -1.01
     seniors
    -1.00
    Senior
    -0.90
     Senior
    -0.80
     Seniors
    -0.75
    ऋ
    -0.72
    <0xA3>
    -0.71
     Collegiate
    -0.71
     XII
    -0.69
    POSITIVE LOGITS
     GCSE
    1.28
     freshman
    1.05
     Freshman
    1.00
     freshmen
    0.94
    Freshman
    0.86
     eighth
    0.78
     ninth
    0.75
    ))[
    0.75
    Sophomore
    0.73
     RMSE
    0.72
    Activations Density 0.014%

    No Known Activations