© 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-65K
    7. 31478
    Prev
    Next
    INDEX
    Explanations

    after spitting or possibility

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Karachi
    0.51
     Paris
    0.48
     museum
    0.46
     PLN
    0.46
     seorang
    0.46
    brahim
    0.46
     Mumbai
    0.45
    H
    0.45
    cry
    0.45
     afbeelding
    0.45
    POSITIVE LOGITS
    頂
    0.43
    ብዙ
    0.43
    他に
    0.41
    洺
    0.41
     wyja
    0.38
     القيمه
    0.38
    [,,"
    0.38
     प्रयासों
    0.37
    toBeTruthy
    0.37
     относи
    0.37
    Activations Density 0.007%

    No Known Activations