© 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. 200726
    Prev
    Next
    INDEX
    Explanations

    dates or months

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

    multiple times, followed by text

    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
    <0x0D>
    0.52
     l
    0.50
     Corollary
    0.49
    ڈ
    0.44
     compartir
    0.43
     glimpse
    0.43
    uyi
    0.43
    ม
    0.43
     ผู้
    0.42
    </span>
    0.42
    POSITIVE LOGITS
     компью
    0.52
     اساس
    0.51
    сход
    0.49
    土壤
    0.48
    碛
    0.47
     имају
    0.47
     народ
    0.46
    hect
    0.46
    然後
    0.46
    高中
    0.46
    Activations Density 0.000%

    No Known Activations