© 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-262K
    7. 11935
    Prev
    Next
    INDEX
    Explanations

    frame rate or geometry

    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_262k_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
    ের
    4.90
    s
    4.54
    ات
    3.65
    к
    3.48
    я
    3.47
    та
    3.46
    ia
    3.42
    िक
    3.34
    ی
    3.27
    ية
    3.21
    POSITIVE LOGITS
    ので
    3.66
    𝐔
    3.58
    𝐌
    3.34
    jší
    3.15
    𝐓
    3.14
    のは
    3.06
    𝐒
    3.03
    ()=>{
    3.00
     расскажем
    2.97
    𝐏
    2.93
    Activations Density 0.031%

    No Known Activations