© 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. 39559
    Prev
    Next
    INDEX
    Explanations

    final exams and projects

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

    The neuron strongly activates on words referring to academic assessments (e.g., “exam,” “exams,” “final,” “examinations,” etc.).

    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
     PUSTAKA
    -1.50
    Maintenant
    -1.12
    icza
    -1.09
     acceptez
    -1.08
     парка
    -1.07
    Dicas
    -1.05
    quées
    -1.05
    eringen
    -1.05
    wanzig
    -1.04
    queur
    -1.03
    POSITIVE LOGITS
     on
    1.64
    地看着
    1.29
     or
    1.20
     for
    1.20
     and
    1.06
     likely
    1.04
    ＠
    1.03
    termine
    1.01
    。“
    1.01
    ころ
    1.01
    Activations Density 0.012%

    No Known Activations