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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79706
    Prev
    Next
    INDEX
    Explanations

    quiz, exam, and practice questions

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

    The neuron fires on words signaling instructions, tasks, or assessments (e.g. “Instructions,” “quiz,” “answers,” “problems,” “tests,” “completion”).

    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
     confronti
    -0.96
     specifics
    -0.96
    팔
    -0.90
    UMENTS
    -0.90
     circumstances
    -0.89
     to
    -0.87
     فهي
    -0.87
     Komponenten
    -0.86
    </h1>
    -0.85
    m
    -0.84
    POSITIVE LOGITS
     quizzes
    1.52
     quiz
    1.30
     test
    1.19
     hôtel
    1.16
     Quizzes
    1.14
     oubli
    1.10
    quiz
    1.09
     golfe
    1.08
    вость
    1.08
     anniversaire
    1.08
    Activations Density 0.023%

    No Known Activations