© 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. 2097
    Prev
    Next
    INDEX
    Explanations

    increasingly

    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
    णिज्य
    2.91
    ש
    2.51
     morphism
    2.47
     tanh
    2.39
    vspace
    2.37
    ณ์
    2.36
    ر
    2.33
     Acids
    2.31
    ্টি
    2.30
    퐫
    2.26
    POSITIVE LOGITS
    т
    3.36
    ت
    3.01
    t
    2.75
    е
    2.66
    uencia
    2.47
    ка
    2.46
    ture
    2.37
    tia
    2.36
    и
    2.33
    ী
    2.26
    Activations Density 0.115%

    No Known Activations