© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28527
    Prev
    Next
    INDEX
    Explanations

    significantly improves or reduces

    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
    堊
    0.49
    ardino
    0.49
    सै
    0.49
     giardino
    0.48
    ار
    0.48
    ruzione
    0.48
    こんばんは
    0.47
    라
    0.47
    කි
    0.46
    انی
    0.46
    POSITIVE LOGITS
     Flex
    0.46
     proves
    0.46
    a
    0.44
     Her
    0.43
     تأثير
    0.43
     Bat
    0.43
     长
    0.41
     அவற்ற
    0.41
     মাধ্যম
    0.41
    Flex
    0.41
    Activations Density 0.004%

    No Known Activations