© 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-262K
    7. 253052
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     độc
    0.46
     independent
    0.41
     peritone
    0.41
    ác
    0.40
     bland
    0.38
     erhältlich
    0.38
    测
    0.38
     missile
    0.38
     बढ़े
    0.38
    Pick
    0.38
    POSITIVE LOGITS
    ოდა
    0.54
    📅
    0.47
    ጠቀ
    0.47
     использова
    0.45
    idam
    0.43
    성화
    0.43
    ્યું
    0.43
    ியது
    0.42
    osia
    0.41
     Voilà
    0.41
    Activations Density 0.003%

    No Known Activations