© 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-65K
    7. 55480
    Prev
    Next
    INDEX
    Explanations

    TO: header

    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_65k_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
     اساس
    0.42
     ලෙස
    0.41
     moguć
    0.40
     ہوں
    0.38
    rsp
    0.38
     behalf
    0.37
     séjour
    0.37
     "//
    0.37
    ަށް
    0.37
     "|"
    0.37
    POSITIVE LOGITS
     compounding
    0.42
     প্রেসিডেন্টের
    0.39
    [['
    0.38
    চন
    0.38
     એમ
    0.37
    ꔰ
    0.36
     accounting
    0.36
    ['
    0.35
    leveland
    0.35
    홉
    0.35
    Activations Density 0.004%

    No Known Activations