© 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. 1870
    Prev
    Next
    INDEX
    Explanations

    `role` or `class`

    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
    瀾
    0.38
     inquiet
    0.38
    ৪১
    0.36
    𒊩
    0.35
    茘
    0.35
     যাত্রা
    0.34
     endExpNow
    0.34
    棹
    0.33
     तलाक
    0.33
     introduit
    0.32
    POSITIVE LOGITS
    class
    0.36
    cache
    0.35
     cast
    0.35
     class
    0.34
     [(
    0.34
    cool
    0.34
    casted
    0.34
     &[
    0.33
     [[[
    0.33
     [[
    0.33
    Activations Density 0.032%

    No Known Activations