© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    operations and how they operate

    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
    {\
    1.42
     recog
    1.39
    朓
    1.37
     balm
    1.31
     мира
    1.27
     atlet
    1.26
     deform
    1.26
     aument
    1.25
     ambivalent
    1.25
     aumento
    1.25
    POSITIVE LOGITS
    ﺮ
    1.50
     sehari
    1.45
    員
    1.42
    ر
    1.36
    day
    1.35
    员
    1.35
     operations
    1.34
    員の
    1.29
    dto
    1.29
    intendent
    1.29
    Activations Density 0.522%

    No Known Activations