© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82667
    Prev
    Next
    INDEX
    Explanations

    nervous confusion stressed inspiration city

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

    logistic regression and neural networks

    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
    Negative Logits
    炤
    0.49
    это
    0.48
     அதிகரித்து
    0.46
    مپ
    0.45
    मैंने
    0.45
    莳
    0.44
    țial
    0.44
     গ্রন্
    0.44
    🛑
    0.43
     женой
    0.43
    POSITIVE LOGITS
    dir
    0.49
     likewise
    0.45
    pard
    0.45
    number
    0.45
    li
    0.43
    bow
    0.43
    market
    0.42
    0.42
    lak
    0.42
    nav
    0.41
    Activations Density 0.006%

    No Known Activations