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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65996
    Prev
    Next
    INDEX
    Explanations

    university names

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

    This neuron detects mentions of universities and other higher-education institutions (e.g., alumni-affiliation tokens).

    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
    毫
    -1.32
    的值
    -1.31
     #
    -1.30
    ˃
    -1.30
    \
    -1.28
     was
    -1.24
    の種類
    -1.23
    ."
    -1.20
     &
    -1.19
    ",
    -1.19
    POSITIVE LOGITS
     zune
    1.44
    četně
    1.39
     ogrodow
    1.38
     totalité
    1.37
    impulan
    1.37
     ユーザー
    1.33
     esame
    1.30
     trattamento
    1.30
    ově
    1.29
    锲
    1.28
    Activations Density 0.070%

    No Known Activations