© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    and / & conjunction

    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
    3.41
     seterusnya
    3.33
    rogens
    3.15
    amp
    3.10
    romeda
    3.00
     sekaligus
    2.92
     sebagainya
    2.92
    諧
    2.87
    ंगाबाद
    2.75
    rews
    2.74
    POSITIVE LOGITS
    一个
    4.72
    м
    3.05
    其他
    3.02
    특별시
    2.96
    一个新的
    2.83
    小朋友
    2.73
     mellitus
    2.64
    ความ
    2.64
    小
    2.50
     eivät
    2.43
    Activations Density 0.453%

    No Known Activations