© 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. 226557
    Prev
    Next
    INDEX
    Explanations

    navigation and discovery

    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
    蛋白質
    0.50
    datap
    0.45
    困難
    0.44
    膾
    0.44
    InitTypeDef
    0.44
    showerror
    0.43
     relato
    0.42
    剞
    0.42
     بتساوي
    0.41
     invariance
    0.41
    POSITIVE LOGITS
    偶尔
    0.50
     zoomed
    0.49
     Ramón
    0.46
     complemented
    0.45
     বাতাসে
    0.45
     occasionally
    0.44
    ệt
    0.43
     dragged
    0.42
     活动
    0.41
     constantemente
    0.41
    Activations Density 0.000%

    No Known Activations