© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26806
    Prev
    Next
    INDEX
    Explanations

    Eminem Marshall Mathers Slim Shady

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     scall
    0.52
    ို
    0.39
    positive
    0.39
    PlatformVersion
    0.38
    ុង
    0.38
    Ukrainian
    0.38
     inactiv
    0.37
    🏾
    0.36
    ভাব
    0.36
     ¼
    0.36
    POSITIVE LOGITS
     Eminem
    0.69
     Slim
    0.59
     Detroit
    0.55
     Marshall
    0.50
    Slim
    0.48
    Detroit
    0.47
     psychotic
    0.47
     relapse
    0.46
     slim
    0.46
     Empor
    0.46
    Activations Density 0.002%

    No Known Activations