© 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. 2189
    Prev
    Next
    INDEX
    Explanations

    Python shines or libraries

    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
    তে
    3.58
    ка
    3.36
    ize
    3.18
    ंदोल
    3.02
    р
    3.02
    ם
    3.02
    на
    2.94
    ITIVE
    2.89
    ים
    2.81
    ర్థిక
    2.81
    POSITIVE LOGITS
    ی
    5.19
    i
    4.51
    ে
    4.46
    ي
    4.28
    י
    4.22
    o
    4.20
    ी
    4.18
    ो
    4.09
    ি
    4.08
    ه
    3.81
    Activations Density 0.573%

    No Known Activations