© 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. 106409
    Prev
    Next
    INDEX
    Explanations

    super, hetero, dys, miss, mis, decor, over, constitu

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

    The neuron strongly responds to isolated Greek‐ or Latin‐derived morphemes (prefixes or roots) that form part of technical/scientific terms.

    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
     правительства
    -1.25
    bisous
    -1.02
    などが
    -0.94
    があるので
    -0.94
     فترة
    -0.93
    があり
    -0.92
     biochemical
    -0.91
     Kräuter
    -0.91
     السياس
    -0.90
    recette
    -0.89
    POSITIVE LOGITS
    購入した
    1.16
    □
    1.11
     Noire
    1.05
    際の
    1.02
    Abbreviations
    1.02
    に追加
    1.02
    ERON
    1.00
    場合には
    0.99
    本日の
    0.98
    каун
    0.98
    Activations Density 0.644%

    No Known Activations