© 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. 40424
    Prev
    Next
    INDEX
    Explanations

    if you

    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
     it
    0.49
     ಅದನ್ನು
    0.47
     contraire
    0.46
     그것
    0.45
     IT
    0.44
     contrary
    0.44
    걔
    0.43
    reib
    0.41
    atique
    0.41
     அதை
    0.41
    POSITIVE LOGITS
    ！
    0.48
    ！)
    0.43
    ；
    0.43
    ！”
    0.42
    疑惑
    0.41
    ！」
    0.41
    ![
    0.40
    ！】
    0.39
     سیل
    0.38
     ਅਤੇ
    0.38
    Activations Density 0.024%

    No Known Activations