© 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. 198484
    Prev
    Next
    INDEX
    Explanations

    approach by, may play

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

    practice test

    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
    촬
    0.47
     уровне
    0.46
     같이
    0.46
     পরে
    0.46
    более
    0.45
    하고
    0.45
     Ва
    0.45
     உப்பு
    0.45
     دریافت‌شده
    0.45
    도
    0.44
    POSITIVE LOGITS
    地产
    0.46
     kontakt
    0.45
     ukaz
    0.45
    ys
    0.44
    增长
    0.44
     رشد
    0.43
    طيني
    0.43
     teria
    0.43
    තික
    0.43
    手机
    0.43
    Activations Density 0.000%

    No Known Activations