© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2114
    Prev
    Next
    INDEX
    Explanations

    LaTeX typesetting and code

    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
    Webhook
    0.49
     assumptive
    0.49
    CRUD
    0.48
    affordable
    0.48
     onboarding
    0.47
    season
    0.46
    RefreshToken
    0.46
    ㅤ
    0.46
    webhook
    0.45
    parentId
    0.45
    POSITIVE LOGITS
     LaTeX
    1.77
    LaTeX
    1.41
     Latex
    1.29
     latex
    1.23
    latex
    1.14
    TeX
    1.10
    documentclass
    1.05
     typesetting
    1.05
    usepackage
    0.95
     arXiv
    0.87
    Activations Density 0.075%

    No Known Activations