© 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. 10-GEMMASCOPE-RES-131K
    7. 128464
    Prev
    Next
    INDEX
    Explanations

    school age groups

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

    The neuron activates strongly on names of schools, academies or secondary institutions and on grade‐ or year‐level designators.

    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
    中です
    -1.38
     weiss
    -1.33
    또
    -1.32
    сток
    -1.29
    也許
    -1.27
     blod
    -1.25
    ៌
    -1.23
    Stap
    -1.18
     Cabrio
    -1.17
    üttel
    -1.16
    POSITIVE LOGITS
     Teens
    1.28
     Teen
    1.25
    Teen
    1.24
     adolescents
    1.23
    ۗ
    1.21
    providedIn
    1.16
    oyant
    1.16
    laining
    1.15
     adolescent
    1.12
     zaji
    1.09
    Activations Density 0.104%

    No Known Activations