© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1749
    Prev
    Next
    INDEX
    Explanations

    international 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_22_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
    नेश्वर
    0.85
     siger
    0.84
    称号
    0.82
    𒈗
    0.81
     Ичиго
    0.79
    💴
    0.78
    দো
    0.77
     tige
    0.77
    <unused334>
    0.76
    <unused952>
    0.76
    POSITIVE LOGITS
    <0xC2>
    0.79
    0.60
     சில
    0.51
    ง
    0.49
    Missense
    0.49
    Opt
    0.48
     Prime
    0.48
    ক্ক
    0.48
     en
    0.48
     dipole
    0.48
    Activations Density 1.573%

    No Known Activations