© 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. 63549
    Prev
    Next
    INDEX
    Explanations

    numbers and health

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

    paragraph line 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
    Negative Logits
     dét
    0.45
     Allerdings
    0.44
    ⇵
    0.44
     ing
    0.43
    がる
    0.43
    ारा
    0.43
    DidLoad
    0.43
    াবন
    0.42
    ПУ
    0.42
     fairs
    0.42
    POSITIVE LOGITS
    linen
    0.50
    一件
    0.48
    plastic
    0.48
    롯
    0.46
    holding
    0.46
     정상
    0.45
    捨
    0.45
    正常
    0.44
    yam
    0.44
    伏
    0.44
    Activations Density 0.000%

    No Known Activations