© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1625
    Prev
    Next
    INDEX
    Explanations

    listing options or examples

    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_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
     whatnot
    2.46
    ات
    2.21
     zwar
    2.11
    romeda
    2.04
    rews
    2.04
    蔼
    2.01
    ோ
    1.93
    िया
    1.91
    諧
    1.87
    ंगाबाद
    1.86
    POSITIVE LOGITS
    一个
    3.36
    其他
    2.75
    一个新的
    2.32
    특별시
    2.31
    服务
    2.27
    ความ
    2.17
    м
    2.04
    с
    2.02
    小伙伴
    1.97
    また
    1.93
    Activations Density 0.107%

    No Known Activations