© 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-262K
    7. 28550
    Prev
    Next
    INDEX
    Explanations

    Latin and variation in language

    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_262k_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
     dashes
    0.40
     Mainland
    0.38
    ellen
    0.38
     redirect
    0.38
     함
    0.37
     doc
    0.37
     verbatim
    0.37
     redirects
    0.36
     dashed
    0.36
     directed
    0.36
    POSITIVE LOGITS
    ordable
    0.49
    啬
    0.42
    umballMachine
    0.42
    ្ម
    0.41
     lesquels
    0.40
    映
    0.40
     dobre
    0.39
    ){}
    0.39
     barato
    0.38
     दक्षि
    0.38
    Activations Density 0.000%

    No Known Activations