© 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. 43313
    Prev
    Next
    INDEX
    Explanations

    Spring Line

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

    Instead of

    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
    下さい
    0.50
     brains
    0.49
     invigor
    0.49
     humankind
    0.49
    ನ
    0.48
     loopholes
    0.48
     purest
    0.47
     woodland
    0.47
     व्यंजनों
    0.47
    갚
    0.47
    POSITIVE LOGITS
    ：“
    0.45
     হে
    0.43
    他在
    0.42
    予測
    0.42
    獬
    0.42
    他和
    0.41
    ্লা
    0.41
    turkish
    0.40
    što
    0.40
    flutter
    0.39
    Activations Density 0.000%

    No Known Activations