© 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. 104461
    Prev
    Next
    INDEX
    Explanations

    health and infrastructure terms

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

    less portable

    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
     Temos
    0.53
    <unused23>
    0.51
     גם
    0.51
     ईमित्र
    0.50
     legislate
    0.50
     автоматы
    0.50
     אוי
    0.49
     monumento
    0.49
    ງ
    0.48
     vaccinate
    0.48
    POSITIVE LOGITS
    ki
    0.58
    iline
    0.56
    ky
    0.50
    ka
    0.50
    0.50
    kart
    0.49
    ier
    0.48
    haft
    0.48
    ert
    0.48
    ale
    0.48
    Activations Density 0.000%

    No Known Activations