© 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. 221283
    Prev
    Next
    INDEX
    Explanations

    status of availability

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

    application text or description

    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
    拍
    0.48
    夺
    0.48
     които
    0.46
    巅
    0.45
     छत
    0.45
    上涨
    0.45
    โอ
    0.44
    拯
    0.43
    蝼
    0.43
    Ӏо
    0.43
    POSITIVE LOGITS
     originated
    0.54
     with
    0.52
     based
    0.50
     through
    0.48
     between
    0.48
     traders
    0.48
     efforts
    0.48
     turquoise
    0.48
     cruisers
    0.48
     possessing
    0.47
    Activations Density 0.001%

    No Known Activations