© 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. 59967
    Prev
    Next
    INDEX
    Explanations

    communication and community outreach

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

    Russia, NATO, Soviet Union

    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
     mindre
    0.58
     McKinney
    0.52
     Solver
    0.48
    蜮
    0.48
    चलिए
    0.46
     أقل
    0.46
    溲
    0.46
     सुधार
    0.44
    Solver
    0.44
    㖪
    0.44
    POSITIVE LOGITS
     exhilarating
    0.46
     beginnings
    0.45
     Alltag
    0.45
     preponderance
    0.44
     heartwarming
    0.44
     everyday
    0.43
    Yeni
    0.43
    extensive
    0.43
     retirees
    0.43
    BufferSize
    0.43
    Activations Density 0.000%

    No Known Activations