© 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. 31-GEMMASCOPE-2-RES-262K
    7. 135260
    Prev
    Next
    INDEX
    Explanations

    cars, precision, portfolio, colored

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     afternoons
    0.40
    zone
    0.39
     aged
    0.38
    gers
    0.38
    तुर
    0.37
     dissolved
    0.37
     and
    0.37
    越
    0.37
    top
    0.36
    this
    0.36
    POSITIVE LOGITS
     toegang
    0.54
     voiture
    0.53
     coche
    0.50
     ragazza
    0.50
    이지만
    0.50
     автомобиль
    0.49
     자동차
    0.49
     köpek
    0.49
     vélo
    0.48
     procédures
    0.48
    Activations Density 0.005%

    No Known Activations