© 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. 40196
    Prev
    Next
    INDEX
    Explanations

    graduation from school

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

    This neuron detects mentions of graduating or graduation (e.g., “graduate,” “graduation,” “graduations”).

    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
     he
    -2.05
     /
    -1.71
    すすめ
    -1.59
    閙
    -1.55
    つけた
    -1.53
    $,
    -1.52
    ୩
    -1.52
    aacute
    -1.50
    ANDUM
    -1.47
    岀
    -1.46
    POSITIVE LOGITS
     precioso
    1.63
    なかなか
    1.55
     soixante
    1.53
     cromado
    1.49
     graduates
    1.48
    一个小
    1.48
     graduation
    1.47
     tabung
    1.45
     Karakter
    1.45
     of
    1.44
    Activations Density 0.030%

    No Known Activations