© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15366
    Prev
    Next
    INDEX
    Explanations

    repentance, salt, calculators, movers

    np_acts-logits-general · gemini-2.5-flash-lite

    explain like I'm five

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    新
    0.29
    ・
    0.29
    或
    0.28
    /
    0.27
    或者
    0.26
    一
    0.26
    As
    0.25
    腾讯
    0.25
    在
    0.25
    One
    0.25
    POSITIVE LOGITS
     ghostly
    0.28
     wretched
    0.26
     murderous
    0.26
     hapless
    0.25
     polypes
    0.25
     sputum
    0.24
     actomyosin
    0.24
     prosent
    0.23
     monstrous
    0.23
     runny
    0.23
    Activations Density 0.212%

    No Known Activations