© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59338
    Prev
    Next
    INDEX
    Explanations

    Exam questions and answers

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

    This neuron fires on question headings and sentences—i.e. lines or phrases formatted as questions (marked by “?” and question‐word structures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    rolls
    -0.88
     musim
    -0.85
     MONDAY
    -0.85
    💁
    -0.85
    MouseAdapter
    -0.82
    против
    -0.81
    tablissements
    -0.81
    Liga
    -0.79
     ..............
    -0.79
     欣赏
    -0.79
    POSITIVE LOGITS
     answer
    1.47
     questions
    1.44
     answers
    1.36
     answering
    1.28
     test
    1.27
     answered
    1.19
     strategy
    1.09
     passages
    1.09
    考生
    1.07
     exam
    1.05
    Activations Density 0.032%

    No Known Activations