© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161011
    Prev
    Next
    INDEX
    Explanations

    what weplace forthe Petitionermaking peoplesys 1can dealgreat deal

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

    ideas and purpose

    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_262k_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
    い
    0.50
    འ
    0.47
     ентите
    0.47
    中の
    0.46
    タイトル
    0.46
     acquainted
    0.46
    いている
    0.45
    出して
    0.45
    编
    0.45
    跹
    0.45
    POSITIVE LOGITS
     n
    0.64
    㧍
    0.50
     Jee
    0.49
     skor
    0.49
    ഽ
    0.48
     Nong
    0.47
    rund
    0.47
    seab
    0.46
    㳊
    0.46
    㕣
    0.46
    Activations Density 0.000%

    No Known Activations