© 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. 130065
    Prev
    Next
    INDEX
    Explanations

    chase and catch

    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
    |(
    0.49
     composé
    0.43
    &(
    0.42
    ниці
    0.40
     ਕਿਸ
    0.40
    avoir
    0.39
     avions
    0.39
    kul
    0.39
    OfType
    0.39
    uZ
    0.38
    POSITIVE LOGITS
    牰
    0.40
    וא
    0.38
     Sigmund
    0.37
     ரீ
    0.36
     ritmo
    0.36
    Detective
    0.35
    Increasing
    0.35
     prints
    0.35
    长大
    0.35
     prosperity
    0.34
    Activations Density 0.002%

    No Known Activations