© 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. 47282
    Prev
    Next
    INDEX
    Explanations

    asking for explanation or clarification

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

    The neuron detects when the text is making a request for code or an explanatory walkthrough.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    haltet
    -0.98
    suggest
    -0.81
     terecht
    -0.77
     victoire
    -0.77
    Suggestions
    -0.76
    ชีวิต
    -0.74
     аккумулятор
    -0.74
     recensement
    -0.73
    msleep
    -0.72
     théâtre
    -0.71
    POSITIVE LOGITS
     explanation
    6.91
     explain
    6.50
     explanations
    6.09
     explained
    5.91
     explaining
    5.69
     explains
    5.47
     Explain
    4.94
    explanation
    4.91
    explain
    4.84
     Explanation
    4.78
    Activations Density 0.222%

    No Known Activations