© 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. 48207
    Prev
    Next
    INDEX
    Explanations

    W followed by German word parts

    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
    amine
    0.44
    }{(\
    0.40
     pince
    0.39
    amples
    0.38
    Moz
    0.38
    nois
    0.38
     fenó
    0.37
    uris
    0.37
     ديك
    0.37
     डोंग
    0.37
    POSITIVE LOGITS
    選択
    0.39
     chọn
    0.38
    issenschaft
    0.38
     wParam
    0.38
    苓
    0.37
     wayside
    0.37
    orthy
    0.36
     верхней
    0.36
     Arma
    0.36
    壁
    0.36
    Activations Density 0.008%

    No Known Activations