© 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. 138110
    Prev
    Next
    INDEX
    Explanations

    foreign languages, specific phrases

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

    demonyms and health terms

    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
     contaminate
    0.48
     gaze
    0.47
    ंचे
    0.46
     cuart
    0.44
    कल
    0.44
    ْت
    0.44
     uncontroll
    0.44
    <0x0D>
    0.43
     iodide
    0.42
     contaminated
    0.42
    POSITIVE LOGITS
     কোনটি
    0.58
     എന്ന്
    0.54
     ตาม
    0.54
     通过
    0.53
     น้ำ
    0.51
     ง
    0.51
     규칙
    0.51
     באמצעות
    0.51
     ช่วย
    0.50
     不需要
    0.50
    Activations Density 0.001%

    No Known Activations