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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    list items with headings

    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
     medicinal
    1.12
     tecnológico
    1.12
    流
    1.11
     genomics
    1.11
     gratis
    1.09
     glows
    1.08
     dùng
    1.08
     genet
    1.07
     technologie
    1.07
     multitud
    1.07
    POSITIVE LOGITS
    চি
    0.80
    :
    0.76
    Т
    0.75
    T
    0.73
    |
    0.72
    Dik
    0.69
    ika
    0.67
     लगती
    0.67
    Stars
    0.67
    s
    0.67
    Activations Density 0.012%

    No Known Activations