© 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. 130054
    Prev
    Next
    INDEX
    Explanations

    Windows Defender, fog

    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
     कलाकार
    0.45
     essa
    0.44
     Europ
    0.43
     l
    0.42
    óis
    0.40
     kon
    0.40
     lt
    0.39
     ul
    0.38
     கலைஞ
    0.38
     encargado
    0.38
    POSITIVE LOGITS
    ⱱ
    0.36
    putting
    0.36
    leaving
    0.36
    examined
    0.35
     Controllers
    0.35
    OnOff
    0.35
    Corporate
    0.35
    উদ্
    0.35
    Controllers
    0.34
     معنا
    0.34
    Activations Density 0.002%

    No Known Activations