© 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. 1070
    Prev
    Next
    INDEX
    Explanations

    things you can

    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
    >/</
    1.31
    टीन
    1.31
     Согласно
    1.28
    সাথে
    1.28
    был
    1.25
    rives
    1.24
     conseguido
    1.23
    मीटर
    1.22
     основе
    1.20
     Regards
    1.20
    POSITIVE LOGITS
    {
    1.41
     never
    1.33
    sak
    1.28
    𝓰
    1.27
    الم
    1.24
    GG
    1.23
    NE
    1.22
     fixing
    1.20
    eis
    1.20
    sb
    1.18
    Activations Density 0.016%

    No Known Activations