© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63208
    Prev
    Next
    INDEX
    Explanations

    meth production or labs

    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
     Preserve
    0.43
    搵
    0.43
     حفظ
    0.42
     prevented
    0.42
     refugees
    0.42
    мережа
    0.41
    듑
    0.41
     Donate
    0.41
     for
    0.40
     Prevent
    0.40
    POSITIVE LOGITS
    \
    0.44
    বল
    0.40
    equation
    0.39
     convincingly
    0.38
     όλα
    0.38
    ！
    0.37
    মণ্ড
    0.37
    盛
    0.37
    💘
    0.36
     showbiz
    0.36
    Activations Density 0.016%

    No Known Activations