© 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. 90785
    Prev
    Next
    INDEX
    Explanations

    make available cases throughout develops

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

    chanting or watching them

    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
     grat
    0.48
     extravag
    0.44
     pla
    0.43
     dol
    0.43
     emphasis
    0.41
     awe
    0.41
    欧元
    0.41
     deng
    0.40
     $\
    0.40
    ドル
    0.40
    POSITIVE LOGITS
     নিয়েই
    0.50
    вніш
    0.49
     নিয়েছেন
    0.48
    getcwd
    0.47
    segaretro
    0.46
    abhavam
    0.46
    न्नई
    0.44
    caused
    0.44
    OUT
    0.43
    utenants
    0.43
    Activations Density 0.001%

    No Known Activations