© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1125
    Prev
    Next
    INDEX
    Explanations

    and continuation

    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_22_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
    一个
    1.24
    ה
    1.00
    м
    0.98
    其他
    0.97
    с
    0.91
    小
    0.90
     However
    0.89
    ا
    0.87
    However
    0.84
    ความ
    0.83
    POSITIVE LOGITS
    romeda
    1.69
    rogens
    1.59
     seterusnya
    1.54
    erson
    1.42
    ंगाबाद
    1.41
    rews
    1.39
    ouille
    1.37
     somit
    1.36
     then
    1.34
     zwar
    1.33
    Activations Density 0.655%

    No Known Activations