© 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. 41-GEMMASCOPE-2-RES-262K
    7. 99453
    Prev
    Next
    INDEX
    Explanations

    medical conditions and technical terms

    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_all/layer_41_width_262k_l0_big
    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
     under
    0.42
    under
    0.42
    shan
    0.37
    Runtime
    0.37
    oshenko
    0.37
    ℝ
    0.37
     கழி
    0.37
    ionalmente
    0.37
    dx
    0.36
     dx
    0.36
    POSITIVE LOGITS
    োজ
    0.41
    ައ
    0.40
    атра
    0.39
    াদশ
    0.39
    кет
    0.38
    атр
    0.38
    TYPE
    0.37
    ゔ
    0.37
    鈐
    0.37
    馬
    0.37
    Activations Density 0.003%

    No Known Activations