© 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. 50538
    Prev
    Next
    INDEX
    Explanations

    scrolling through entertainment and lists

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

    life seems / arise seems

    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
     sparrow
    0.44
     سپس
    0.44
    ス
    0.43
     SAL
    0.42
    疾患
    0.42
    na
    0.42
     SEARCH
    0.42
    Subsequently
    0.41
     TOUR
    0.41
    SOURCES
    0.40
    POSITIVE LOGITS
    玩意
    0.47
     ครอง
    0.46
     Oprah
    0.44
     Amitabh
    0.44
    娱乐圈
    0.43
    娱
    0.42
    涧
    0.41
     Kabhi
    0.41
    ুপ্ত
    0.40
     contrived
    0.40
    Activations Density 0.000%

    No Known Activations