© 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. 218005
    Prev
    Next
    INDEX
    Explanations

    increase, expertise, Ket, file, yet, encodes

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

    greetings

    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
    대학교
    0.48
    大學
    0.46
    日本
    0.46
    亞
    0.46
    R
    0.45
    V
    0.45
    University
    0.44
    ਿੰ
    0.43
    5
    0.43
    6
    0.43
    POSITIVE LOGITS
     kebak
    0.48
     quiescent
    0.48
     austerity
    0.44
     exertion
    0.43
     curative
    0.43
     equilibrio
    0.43
     causative
    0.42
     quies
    0.42
     exertions
    0.42
    しましたが
    0.42
    Activations Density 0.001%

    No Known Activations