© 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. 62542
    Prev
    Next
    INDEX
    Explanations

    common phrases

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

    The neuron is strongly active on the core words of “definition” sentences—i.e. the subject‐is‐predicate patterns that actually define or describe the thing under discussion.

    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
     this
    -0.87
     some
    -0.85
     lavish
    -0.84
     efficiently
    -0.83
     Stephen
    -0.82
     Himmels
    -0.82
     people
    -0.79
     changes
    -0.79
     confirms
    -0.79
     enhances
    -0.79
    POSITIVE LOGITS
    ﾕ
    1.00
     الدولية
    0.98
     galley
    0.94
    рюкзак
    0.92
    ingual
    0.90
    UNKNOWN
    0.87
     コットン
    0.86
    quatre
    0.86
    alisation
    0.85
    WHY
    0.85
    Activations Density 0.002%

    No Known Activations