© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15596
    Prev
    Next
    INDEX
    Explanations

    classification codes and goods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    琚
    0.97
    柟
    0.96
    время
    0.94
     সূচনা
    0.90
     Cllr
    0.86
    ਲ
    0.84
    櫒
    0.83
    ciende
    0.81
     这
    0.81
     هذ
    0.81
    POSITIVE LOGITS
     บ้าง
    0.72
     Force
    0.69
    โร
    0.68
     Sext
    0.68
    बारी
    0.67
    UserState
    0.67
    τικές
    0.66
     Hun
    0.66
     zy
    0.66
     Gourmet
    0.65
    Activations Density 0.002%

    No Known Activations