© 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. 21270
    Prev
    Next
    INDEX
    Explanations

    What followed by I or you

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

    what explaining

    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
    人了
    0.43
     ગયો
    0.42
    텍
    0.41
    Ꮶ
    0.41
    ێن
    0.41
     왜
    0.40
     تلوار
    0.40
    WorkingDirectory
    0.40
    荅
    0.39
    籹
    0.39
    POSITIVE LOGITS
    注意的是
    0.57
    最为
    0.46
     ushered
    0.45
    itioners
    0.44
     सुकून
    0.44
     drawback
    0.43
    urses
    0.43
     downside
    0.43
     intéressant
    0.43
    ab
    0.42
    Activations Density 0.103%

    No Known Activations