© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21790
    Prev
    Next
    INDEX
    Explanations

    Biochemistry and Bach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彪
    0.42
    优秀的
    0.41
     कुलकर्णी
    0.40
    规定
    0.39
    邮箱
    0.39
    exempl
    0.38
    ठे
    0.38
    摘
    0.38
     ಸ್ಥಾನ
    0.38
     स्कूली
    0.38
    POSITIVE LOGITS
     bah
    0.45
    arier
    0.39
     Nothing
    0.39
    ForItem
    0.38
    stein
    0.38
    ISES
    0.38
    celona
    0.37
     NOTHING
    0.37
     accorded
    0.36
    leda
    0.36
    Activations Density 0.002%

    No Known Activations