© 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. 172074
    Prev
    Next
    INDEX
    Explanations

    marketing, business, processes

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

    within or by sections

    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
     tasked
    0.54
     suppl
    0.52
     prosp
    0.48
     wers
    0.47
     noved
    0.47
     सुधा
    0.47
     langfrist
    0.47
    砶
    0.47
    ocyst
    0.46
     بەر
    0.45
    POSITIVE LOGITS
    sik
    0.49
     Lamb
    0.43
    orang
    0.42
     lemah
    0.42
     된
    0.41
     '+':
    0.41
     kepada
    0.41
     আজও
    0.39
    stethoscope
    0.39
    Does
    0.39
    Activations Density 0.001%

    No Known Activations