© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130832
    Prev
    Next
    INDEX
    Explanations

    Dao, imperial China, jade

    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
    鲸
    0.46
    鋯
    0.45
    嗉
    0.42
    ﹂
    0.41
    ಕ್ಷಣ
    0.41
    BURG
    0.41
     যের
    0.41
    栅
    0.41
    輥
    0.41
    頜
    0.40
    POSITIVE LOGITS
     imperial
    0.46
    dao
    0.44
     Dao
    0.42
    Dao
    0.41
     da
    0.41
     fork
    0.41
     Imperial
    0.41
    민
    0.39
     jade
    0.39
     implicate
    0.38
    Activations Density 0.002%

    No Known Activations