© 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. 17-GEMMASCOPE-2-RES-16K
    7. 11310
    Prev
    Next
    INDEX
    Explanations

    use your senses

    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
    k
    0.85
    관계
    0.85
    構
    0.82
    いた
    0.75
    cbc
    0.72
    ================
    0.70
    ни
    0.69
    Ali
    0.68
    nh
    0.68
    ""
    0.68
    POSITIVE LOGITS
    ástica
    1.16
    Sementara
    1.06
     interrogation
    1.06
    मीटर
    1.06
     Tại
    1.03
     terrifying
    1.03
    皞
    1.01
     disappointment
    1.00
     jūs
    0.97
    Ỹ
    0.97
    Activations Density 0.003%

    No Known Activations