© 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. 31390
    Prev
    Next
    INDEX
    Explanations

    words introducing clauses

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

    airways when

    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
    ພ
    0.55
    sson
    0.52
     использовали
    0.51
    ปิด
    0.50
    襷
    0.49
    $\$
    0.48
     decembrie
    0.48
    З
    0.48
    dos
    0.48
     κάν
    0.47
    POSITIVE LOGITS
     spores
    0.57
     Awareness
    0.54
     receptors
    0.51
     ovaries
    0.49
    لوث
    0.47
    itte
    0.46
     Yankees
    0.46
    راف
    0.46
     Uranium
    0.46
     phospholipid
    0.45
    Activations Density 0.000%

    No Known Activations