© 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-262K
    7. 139491
    Prev
    Next
    INDEX
    Explanations

    brackets and phrases

    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
     تمہ
    0.48
    સ્યા
    0.47
    н
    0.47
     المرس
    0.44
    ურად
    0.43
     recessive
    0.43
    得多
    0.43
    nelle
    0.43
    י
    0.42
    ናል
    0.42
    POSITIVE LOGITS
    ung
    0.49
    ior
    0.49
     daqui
    0.48
    az
    0.48
    ừng
    0.47
    ottest
    0.46
    çi
    0.46
    庫
    0.46
     Jap
    0.45
    ड्डी
    0.44
    Activations Density 0.001%

    No Known Activations