© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56951
    Prev
    Next
    INDEX
    Explanations

    detects yes or no answers

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

    This neuron detects affirmations in Q&A contexts, i.e. phrases where a question is answered with “yes” (e.g. “answered YES,” “the answer is yes”).

    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
     saying
    -0.86
    Say
    -0.85
    anson
    -0.81
     authorized
    -0.80
     harmful
    -0.79
    ି
    -0.79
     ragazzo
    -0.77
     oznac
    -0.76
     servizi
    -0.75
    癥
    -0.75
    POSITIVE LOGITS
     yes
    1.22
     "
    1.13
     “
    1.07
     no
    1.07
     ‘
    0.97
    Heck
    0.97
    YES
    0.95
     Heck
    0.89
     YES
    0.89
     NO
    0.87
    Activations Density 0.016%

    No Known Activations