© 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. 227047
    Prev
    Next
    INDEX
    Explanations

    appearance, latest, details

    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
    会長
    0.46
    法則
    0.46
    感覚
    0.44
     deficits
    0.44
    pageControl
    0.44
    オリン
    0.44
    氾
    0.44
    これらの
    0.44
    ತರ
    0.44
     combinatorial
    0.43
    POSITIVE LOGITS
    模样
    0.53
     Terbaru
    0.45
    ี้
    0.45
    ayette
    0.43
    Charter
    0.43
     деталей
    0.43
    的样子
    0.43
    ڽ
    0.42
    鬃
    0.42
    SwingConstants
    0.41
    Activations Density 0.000%

    No Known Activations