© 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. 1968
    Prev
    Next
    INDEX
    Explanations

    repeating blocks of characters

    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
    로
    4.53
    𝘴
    3.83
    𝐳
    3.62
    ான
    3.47
    ar
    3.46
    𝘨
    3.36
    ত
    3.33
     virial
    3.33
    𝘤
    3.26
    ć
    3.24
    POSITIVE LOGITS
    ੀ
    3.67
    ی
    3.45
    i
    3.15
    ি
    3.07
    특별시
    3.03
    ıda
    2.96
    𝙮
    2.93
    𝙞
    2.84
    eel
    2.81
    𝙖
    2.77
    Activations Density 0.609%

    No Known Activations