© 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. 21783
    Prev
    Next
    INDEX
    Explanations

    full screen modes

    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
     hyperactivity
    0.45
     движение
    0.43
    ırlar
    0.40
    }}{
    0.40
     حوالہ
    0.39
    を受
    0.39
     Error
    0.38
     স্থলে
    0.38
    すなわち
    0.37
     voyages
    0.37
    POSITIVE LOGITS
    Full
    0.40
    森
    0.40
    LOY
    0.39
    Nic
    0.39
    лья
    0.39
    恹
    0.39
     క్ర
    0.38
     full
    0.38
     Kre
    0.38
     cre
    0.36
    Activations Density 0.000%

    No Known Activations