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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3590
    Prev
    Next
    INDEX
    Explanations

    articles and determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    )}=\
    2.43
     (\%)
    2.40
     historians
    2.23
     &/
    2.20
    istency
    2.18
     (%)
    2.18
    ppage
    2.18
     criticised
    2.16
     McKin
    2.14
    篑
    2.13
    POSITIVE LOGITS
     một
    3.47
     a
    3.39
     sebuah
    3.33
    一个
    2.96
    một
    2.73
    一座
    2.71
    一個
    2.70
    一个新的
    2.69
    一款
    2.64
     een
    2.62
    Activations Density 0.707%

    No Known Activations