© 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. 2492
    Prev
    Next
    INDEX
    Explanations

    DeepMind and its origins

    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
     可以
    0.29
     উৎপ
    0.29
     mensual
    0.28
     fà
    0.28
     signup
    0.28
     来自
    0.28
     чтоб
    0.28
    㤈
    0.28
     uninterrupted
    0.28
    सिला
    0.27
    POSITIVE LOGITS
    who
    0.38
     quien
    0.37
     who
    0.36
     selaku
    0.35
    whom
    0.35
     الذين
    0.33
    uku
    0.32
     subsidiary
    0.32
    iva
    0.32
     आणि
    0.32
    Activations Density 0.012%

    No Known Activations