© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 440
    Prev
    Next
    INDEX
    Explanations

    built it so far

    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
    此之外
    1.78
    cstdlib
    1.72
    \%,
    1.69
     transfected
    1.67
    ción
    1.65
     ",",
    1.61
     `${
    1.57
    烬
    1.56
    pluck
    1.55
    𝑉
    1.54
    POSITIVE LOGITS
    いる
    1.75
    สรร
    1.75
     dựng
    1.71
    दिव
    1.68
    ла
    1.67
     sefer
    1.65
    ership
    1.64
     onda
    1.59
     впечатление
    1.55
     consenso
    1.51
    Activations Density 1.123%

    No Known Activations