© 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. 137709
    Prev
    Next
    INDEX
    Explanations

    et al

    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
     मोहन
    0.40
    ayon
    0.39
    irmingham
    0.38
    John
    0.37
     www
    0.36
     Archbishop
    0.36
    Arizona
    0.36
     W
    0.35
    www
    0.35
     मर
    0.35
    POSITIVE LOGITS
    ત્તા
    0.46
     Gao
    0.43
    遌
    0.42
     ihan
    0.41
    攽
    0.41
     espacial
    0.40
    હુ
    0.38
     contribuer
    0.38
     nain
    0.38
     (-\
    0.38
    Activations Density 0.001%

    No Known Activations