© 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. 63441
    Prev
    Next
    INDEX
    Explanations

    programs, billions, 737, alternative milk

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

    offers common arguments and plot

    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
     o
    0.49
    spec
    0.47
    :
    0.47
    CTE
    0.46
    ait
    0.45
    preset
    0.45
     atau
    0.45
    calculated
    0.45
    termin
    0.44
    hyd
    0.44
    POSITIVE LOGITS
     pabbaj
    0.55
     சம்பவ
    0.49
     rheumatism
    0.48
    ى
    0.48
    ंगिक
    0.48
     mús
    0.48
     eloquence
    0.47
     sheaf
    0.47
     martyrs
    0.46
     sheaves
    0.46
    Activations Density 0.000%

    No Known Activations