© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7130
    Prev
    Next
    INDEX
    Explanations

    large numbers in millions or billions

    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_22_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
     २४
    0.84
     ९
    0.75
     surpassing
    0.73
    更多的
    0.67
    更多
    0.66
     ७
    0.65
     종합
    0.64
    तरंज
    0.63
     weekend
    0.62
    osulf
    0.62
    POSITIVE LOGITS
     million
    1.11
    million
    1.06
     Million
    1.05
    Million
    1.03
     ล้าน
    1.00
    万
    0.99
     milion
    0.98
     millió
    0.97
     مليون
    0.97
     Millionen
    0.96
    Activations Density 0.150%

    No Known Activations