© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2869
    Prev
    Next
    INDEX
    Explanations

    divides en pasos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     клі
    0.57
     гуляць
    0.52
    ває
    0.52
    盯着
    0.51
     вікі
    0.50
     потім
    0.49
    箓
    0.49
     прадстаў
    0.49
     якая
    0.49
     толькі
    0.48
    POSITIVE LOGITS
     Perú
    1.07
     México
    1.05
     proyect
    0.98
     Universidad
    0.97
     ¿
    0.93
    ´
    0.93
     frecu
    0.93
     más
    0.92
     María
    0.91
     adecu
    0.91
    Activations Density 0.086%

    No Known Activations