© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1063
    Prev
    Next
    INDEX
    Explanations

    particulate matter

    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
     উঠিয়া
    1.36
     kis
    1.32
     життя
    1.32
    ಯಲ್ಲಿ
    1.31
    ยนต์
    1.29
    parseLong
    1.27
    턴
    1.26
    ๓
    1.25
    conversation
    1.25
    csproj
    1.25
    POSITIVE LOGITS
    𝗢
    1.19
    gomery
    1.09
    ic
    1.04
    acas
    1.03
    א
    0.99
    ছেন
    0.98
    ката
    0.98
    പ്പെടുന്നു
    0.97
    asted
    0.97
    odat
    0.96
    Activations Density 0.000%

    No Known Activations