© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8334
    Prev
    Next
    INDEX
    Explanations

    presidents and prime ministers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    idan
    1.24
    俦
    1.20
    ók
    1.19
    opian
    1.19
     service
    1.12
     Zeitschrift
    1.11
     charity
    1.11
    rim
    1.06
     Repert
    1.03
    rimin
    1.03
    POSITIVE LOGITS
     wann
    2.11
    ＿＿
    2.08
     pout
    2.07
    迭代
    2.05
    懑
    2.01
     sleepless
    2.01
     herkes
    1.99
    odymyr
    1.99
     appr
    1.99
    喊
    1.98
    Activations Density 0.111%

    No Known Activations