© 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. 10-GEMMASCOPE-RES-131K
    4. 41286
    Prev
    Next
    INDEX
    Explanations

    school types and levels

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

    The neuron is looking for words that indicate educational institutions or school levels (e.g., “Primary,” “Intermediate,” “College,” “Secondary,” “School”).

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

    No Comments

    Negative Logits
     Different
    -1.30
     diferite
    -1.27
    اقرأ
    -1.26
     разные
    -1.25
    它的
    -1.21
    different
    -1.20
    laient
    -1.20
    Different
    -1.18
    不同的
    -1.16
     både
    -1.15
    POSITIVE LOGITS
     will
    1.77
     how
    1.76
     those
    1.66
     where
    1.52
     who
    1.48
     other
    1.37
    :……
    1.32
    gilet
    1.28
    florida
    1.27
     your
    1.24
    Activations Density 0.045%

    No Known Activations