© 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. 29-GEMMASCOPE-2-RES-16K
    7. 679
    Prev
    Next
    INDEX
    Explanations

    data into actionable insights

    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_29_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
     :)
    1.64
     đc
    1.56
     usw
    1.55
     =)
    1.51
     lots
    1.48
    이랑
    1.47
     veldig
    1.46
     :-)
    1.44
    !!!
    1.43
    すごく
    1.40
    POSITIVE LOGITS
     myriad
    1.48
     replete
    1.38
     burgeoning
    1.36
     requisite
    1.25
     lauded
    1.24
     heralded
    1.24
     veritable
    1.21
     invariably
    1.20
     adept
    1.20
     undeniably
    1.20
    Activations Density 1.835%

    No Known Activations