© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249896
    Prev
    Next
    INDEX
    Explanations

    temporary powerups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     drawbacks
    0.55
     egent
    0.46
     kanssa
    0.45
     빠
    0.45
     소
    0.44
     bana
    0.44
     asignatura
    0.44
     부족
    0.44
     inadequacy
    0.43
     damal
    0.43
    POSITIVE LOGITS
    cort
    0.49
    慥
    0.49
    localStorage
    0.46
     юриди
    0.45
     להיות
    0.45
    nvim
    0.45
    ವಿಧ
    0.44
    柊
    0.44
     Penit
    0.44
    નગર
    0.44
    Activations Density 0.000%

    No Known Activations