© 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. 24637
    Prev
    Next
    INDEX
    Explanations

    exp, exped, expo variations

    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
    ewek
    0.45
     philanth
    0.43
    asambhavam
    0.41
     Swinging
    0.41
     характери
    0.41
    ।.
    0.40
     المسافه
    0.40
    alion
    0.40
     Aham
    0.39
    ನ
    0.39
    POSITIVE LOGITS
     exp
    0.91
     Exp
    0.77
     EXP
    0.75
     एक्सप
    0.67
    EXP
    0.66
     expo
    0.65
     Expo
    0.64
    Expo
    0.62
     xp
    0.62
    Exp
    0.61
    Activations Density 0.034%

    No Known Activations