© 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-262K
    7. 128521
    Prev
    Next
    INDEX
    Explanations

    visual observation

    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_262k_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
     जाओ
    0.55
     Bây
    0.50
     nue
    0.50
     hô
    0.48
     रहो
    0.47
    ၿ
    0.46
     Sichuan
    0.46
     MSD
    0.45
     rå
    0.44
     Guangdong
    0.44
    POSITIVE LOGITS
     Ratings
    0.43
    質
    0.42
     varies
    0.41
    ниях
    0.41
    ਿਤ
    0.40
    nä
    0.38
    Lessons
    0.38
     summation
    0.38
    ள்ளார்
    0.38
     can
    0.38
    Activations Density 0.003%

    No Known Activations