© 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. 31-GEMMASCOPE-2-RES-65K
    7. 30477
    Prev
    Next
    INDEX
    Explanations

    finance, health, and technical processes

    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_31_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
    的
    0.45
    δ
    0.41
    는
    0.40
    assertRaises
    0.39
     følge
    0.39
     endorsed
    0.39
    際
    0.38
    遵循
    0.38
    適合
    0.36
    は
    0.36
    POSITIVE LOGITS
     Много
    0.48
     Ethnic
    0.46
     Accordingly
    0.45
     Seafood
    0.45
     Abhäng
    0.44
     півні
    0.44
     Sitting
    0.44
     několika
    0.44
    ปลาย
    0.44
    żenie
    0.44
    Activations Density 0.023%

    No Known Activations