© 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-65K
    7. 14862
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and urls

    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
    初步
    0.46
     {#
    0.42
     长
    0.41
    \*
    0.41
    ℍ
    0.40
     展示
    0.40
     italic
    0.39
    正则表达式
    0.39
    ﻩ
    0.39
    ዥ
    0.39
    POSITIVE LOGITS
     Links
    0.51
     pierde
    0.51
     LINKS
    0.50
    سك
    0.49
     límite
    0.48
    صدر
    0.47
    adeva
    0.46
    들이
    0.45
    Links
    0.45
    сход
    0.45
    Activations Density 0.001%

    No Known Activations