© 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. 22-GEMMASCOPE-RES-131K
    7. 64322
    Prev
    Next
    INDEX
    Explanations

    Empowering, friends, reassure, I can

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

    The neuron activates specifically on the word “friends.”

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fermer
    -1.13
     perles
    -1.11
    に追加
    -1.09
     imprimer
    -1.08
     SITY
    -1.08
    öscht
    -1.05
    ラッキー
    -1.04
     APPELL
    -0.99
    Daha
    -0.99
    おわりに
    -0.98
    POSITIVE LOGITS
     to
    1.27
     algunas
    1.03
    大幅
    0.99
     invece
    0.96
    努力
    0.94
    微笑
    0.93
     are
    0.92
     was
    0.90
     algunos
    0.89
    籁
    0.89
    Activations Density 0.000%

    No Known Activations