© 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. 208187
    Prev
    Next
    INDEX
    Explanations

    sciences cluster

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

    clarify, students, polarization, structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Depend
    0.49
    кто
    0.48
    平均
    0.46
    创建
    0.45
     života
    0.45
     හැකිය
    0.44
    值
    0.44
    哪個
    0.43
    乘
    0.43
     přev
    0.42
    POSITIVE LOGITS
    Jin
    0.56
    Positions
    0.54
     PKK
    0.51
    liang
    0.50
    abelian
    0.50
    Ling
    0.50
     aton
    0.50
    Vill
    0.50
    Yun
    0.50
    Khan
    0.50
    Activations Density 0.000%

    No Known Activations