© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13470
    Prev
    Next
    INDEX
    Explanations

    years in parentheses

    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_17_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
    পূর্ব
    1.57
    ₱
    1.35
    ᵉ
    1.35
    fps
    1.34
    氪
    1.34
     kır
    1.32
    必要があります
    1.29
    우스
    1.29
    ethers
    1.28
     headlined
    1.28
    POSITIVE LOGITS
    ل
    1.71
    其他
    1.67
    いう
    1.55
     circumstances
    1.48
    gäng
    1.43
    tedir
    1.39
    Connections
    1.39
    वळ
    1.36
    lication
    1.36
    ात
    1.35
    Activations Density 0.022%

    No Known Activations