© 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. 36369
    Prev
    Next
    INDEX
    Explanations

    North Korea

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

    language and context related to color

    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
    -
    0.55
    (
    0.48
    {-
    0.47
     (**
    0.47
     (‘
    0.45
    -<
    0.43
     (>
    0.43
    安全
    0.42
     ως
    0.42
    졸
    0.42
    POSITIVE LOGITS
     இறந்த
    0.48
     tiktok
    0.48
    ರ್ಗ
    0.46
     hõ
    0.45
     सुनेंरोक
    0.45
    нє
    0.44
    ቱም
    0.44
     검색
    0.44
     व्हिडीओ
    0.44
     encontrar
    0.43
    Activations Density 0.001%

    No Known Activations