© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79247
    Prev
    Next
    INDEX
    Explanations

    compiled code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marvin
    -0.82
    Marvin
    -0.81
     المحت
    -0.74
    疥
    -0.73
    邝
    -0.70
     Animator
    -0.70
    Deleting
    -0.69
    compati
    -0.68
     concealer
    -0.68
    δει
    -0.68
    POSITIVE LOGITS
    WEB
    0.73
     Idea
    0.71
     feral
    0.70
     Systems
    0.69
    处理
    0.69
    未満
    0.68
    alted
    0.68
    bindParam
    0.68
    у
    0.68
    婭
    0.68
    Activations Density 0.026%

    No Known Activations