© 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. 2606
    Prev
    Next
    INDEX
    Explanations

    install and setup

    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
     diathermy
    0.49
    否定
    0.45
     impractic
    0.40
    деа
    0.40
     conductas
    0.39
     probative
    0.39
    ‖
    0.39
     diurnal
    0.38
     الحصه
    0.38
    族
    0.38
    POSITIVE LOGITS
     install
    1.52
    Install
    1.45
    安装
    1.45
     installieren
    1.42
     Install
    1.41
     installation
    1.40
     installing
    1.40
     설치
    1.38
     Installing
    1.37
    インストール
    1.35
    Activations Density 0.661%

    No Known Activations