© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 13761
    Prev
    Next
    INDEX
    Explanations

    mathematical values and operations

    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_262k_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
     crappy
    1.18
     onboarding
    1.06
    odigd
    1.06
    ▻
    1.05
    🠀
    1.00
     proactively
    0.98
     imperatives
    0.97
    📞
    0.94
    ➢
    0.94
     통해
    0.93
    POSITIVE LOGITS
    的值
    1.24
     value
    1.14
    整数
    1.11
    値
    1.06
    值
    1.04
    最小值
    1.03
    Value
    1.01
    sqrt
    0.98
     integers
    0.98
     values
    0.97
    Activations Density 0.169%

    No Known Activations