© 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. 21519
    Prev
    Next
    INDEX
    Explanations

    example targets

    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
    ަ
    0.40
     계약
    0.39
    मुख्य
    0.38
    אם
    0.36
     फिलहाल
    0.36
     шаблон
    0.36
     полити
    0.35
     إذا
    0.35
     രാഷ്ട്രീയ
    0.35
     കരാ
    0.35
    POSITIVE LOGITS
     over
    0.41
     using
    0.38
     from
    0.38
     %.
    0.35
    +.
    0.35
     compared
    0.34
     +
    0.34
     $
    0.34
    居然
    0.34
     suboptimal
    0.34
    Activations Density 0.002%

    No Known Activations