© 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. 10-GEMMASCOPE-RES-131K
    7. 105022
    Prev
    Next
    INDEX
    Explanations

    university or college names

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

    The neuron specializes in spotting mentions of universities or other higher‐education institutions.

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

    mentions of universities and other educational institutions, especially references to graduating and academic degrees in biographies.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to university names and associated degree information in biographical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     its
    -2.03
    its
    -1.64
     that
    -1.40
    这些
    -1.34
     suoi
    -1.29
     these
    -1.28
     эти
    -1.28
    它的
    -1.26
    Its
    -1.17
    其
    -1.16
    POSITIVE LOGITS
     teníamos
    1.33
    esserts
    1.32
    blouse
    1.27
    ualaikum
    1.20
    щення
    1.20
    utnant
    1.19
     során
    1.15
    aulted
    1.13
    Bises
    1.12
    valier
    1.11
    Activations Density 0.091%

    No Known Activations