© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34703
    Prev
    Next
    INDEX
    Explanations

    Dirichlet distribution

    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_all/layer_41_width_262k_l0_big
    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
     coro
    0.45
     찾
    0.43
     Voz
    0.41
     नस
    0.40
    ᖁ
    0.40
    ὤ
    0.40
    휩
    0.40
    ွ
    0.39
     Hwang
    0.38
    turno
    0.38
    POSITIVE LOGITS
     dir
    0.63
    Dir
    0.60
     Dirichlet
    0.57
     Dir
    0.55
     Dirk
    0.49
    dir
    0.47
     kg
    0.42
     Dirac
    0.42
     subdiv
    0.41
     floors
    0.41
    Activations Density 0.000%

    No Known Activations