© 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. 128777
    Prev
    Next
    INDEX
    Explanations

    This neuron detects mentions of “High School” (i.e., references to attending or naming a high school).

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

    seasons, junior, champion, earned

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    盉
    -1.29
     včetně
    -1.23
     niega
    -1.21
     réinitial
    -1.20
    vangen
    -1.19
     invertir
    -1.19
     ocultar
    -1.18
    我們
    -1.18
    していますが
    -1.18
     repuesto
    -1.17
    POSITIVE LOGITS
     also
    1.55
     senhora
    1.24
     school
    1.17
    کہ
    1.14
     donde
    1.14
     las
    1.13
     également
    1.13
     Stadtteil
    1.05
    viä
    1.05
    til
    1.04
    Activations Density 0.033%

    No Known Activations