© 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. 81717
    Prev
    Next
    INDEX
    Explanations

    computer hardware and logic

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

    comparison and calculation

    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
    ят
    0.50
    ם
    0.50
    ྰ
    0.43
     thermometers
    0.43
     sprink
    0.43
    ర్ప
    0.43
    Miami
    0.43
     дал
    0.43
    டாக
    0.43
    酊
    0.42
    POSITIVE LOGITS
    concurrent
    0.48
     PCIe
    0.46
     Macron
    0.44
     IPv
    0.44
     Qi
    0.43
    removeFrom
    0.43
     Zukunft
    0.43
     দুঃ
    0.43
    dete
    0.43
    prevState
    0.42
    Activations Density 0.002%

    No Known Activations