© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10351
    Prev
    Next
    INDEX
    Explanations

    eye contact

    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_9_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
    ل
    1.81
    不
    1.57
    到的
    1.55
    不管
    1.50
    ческих
    1.47
    ब्दिक
    1.47
    el
    1.44
    얹
    1.39
    無需
    1.36
    n
    1.36
    POSITIVE LOGITS
    гістра
    1.55
     industrialized
    1.55
     Đảng
    1.47
     ​​
    1.46
    ยะ
    1.45
     ग्ले
    1.43
     ря
    1.37
     genders
    1.34
     cartes
    1.34
     Wahl
    1.34
    Activations Density 0.006%

    No Known Activations