© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    code block formatting

    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
     (**
    0.39
     итоге
    0.38
     trajectories
    0.38
     asymptotics
    0.37
     '!
    0.34
     też
    0.34
     đẩy
    0.33
     juga
    0.33
     topologically
    0.33
     esque
    0.33
    POSITIVE LOGITS
    #
    0.50
    H
    0.48
    K
    0.45
    W
    0.44
    S
    0.43
    କ
    0.42
    C
    0.41
    Either
    0.41
    お
    0.41
    that
    0.40
    Activations Density 0.261%

    No Known Activations