© 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. 52395
    Prev
    Next
    INDEX
    Explanations

    latex environments (align, cases, itemize)

    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
     four
    0.37
     resultMap
    0.37
     typography
    0.36
     ряд
    0.36
     |--
    0.36
     Makefile
    0.36
    cn
    0.36
     कां
    0.36
    x
    0.36
     四
    0.36
    POSITIVE LOGITS
    र्सन
    0.40
    स्तिष्क
    0.39
    EnableCOMDAT
    0.39
    Acknowledg
    0.39
     stew
    0.38
     pastures
    0.38
    apadam
    0.38
    喧
    0.38
     বাহিরে
    0.38
    setScene
    0.37
    Activations Density 0.003%

    No Known Activations