© 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-16K
    7. 5826
    Prev
    Next
    INDEX
    Explanations

    math and physics notation

    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_16k_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
    身份证
    0.41
    馀
    0.39
     Processing
    0.38
     прозра
    0.37
    imbledon
    0.37
    inline
    0.36
    领域
    0.36
    该
    0.36
    toContain
    0.36
    ----------------
    0.35
    POSITIVE LOGITS
     denoted
    0.75
    denoted
    0.70
     $\
    0.63
     ${\
    0.57
     H
    0.53
     ϕ
    0.53
     θ
    0.53
     (_
    0.53
     Q
    0.52
     R
    0.52
    Activations Density 0.432%

    No Known Activations