© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130970
    Prev
    Next
    INDEX
    Explanations

    activities and capabilities

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

    fast declines, Savings start

    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
    概念
    0.50
    那麼
    0.49
    聖
    0.47
    з
    0.47
    那個
    0.46
    這個
    0.45
    ИТ
    0.45
    的概念
    0.45
    累積
    0.44
    厸
    0.44
    POSITIVE LOGITS
     terg
    0.49
     renseignements
    0.49
     adım
    0.48
     logins
    0.48
     subsec
    0.47
     manganese
    0.47
     Subsec
    0.46
     faaliyet
    0.46
     ferroc
    0.46
     kerusakan
    0.45
    Activations Density 0.000%

    No Known Activations