© 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-16K
    7. 9486
    Prev
    Next
    INDEX
    Explanations

    AWS Step

    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_16k_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
     Å
    0.46
    িমূলক
    0.42
     Wear
    0.41
    ㄨ
    0.40
    го
    0.39
     wParam
    0.39
     roce
    0.38
     Incredible
    0.38
    র্তি
    0.38
     å
    0.37
    POSITIVE LOGITS
    IW
    0.50
    esome
    0.50
    INDOW
    0.48
    PW
    0.48
    Dew
    0.48
    baw
    0.47
    itzerland
    0.46
    DW
    0.45
     IW
    0.44
    LW
    0.44
    Activations Density 0.303%

    No Known Activations