© 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. 47130
    Prev
    Next
    INDEX
    Explanations

    names starting with Mc

    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
    Negative Logits
    Fonte
    -0.73
    enosine
    -0.72
    Recipes
    -0.71
    Dairy
    -0.71
     werden
    -0.71
    唆
    -0.70
    Critique
    -0.70
     картина
    -0.69
     auditing
    -0.68
    ちは
    -0.67
    POSITIVE LOGITS
    ech
    0.85
    ところに
    0.85
    ॰
    0.85
    いった
    0.78
    🇷
    0.77
    ONA
    0.77
    /}
    0.76
     besluit
    0.75
     eingestellt
    0.75
    悚
    0.75
    Activations Density 0.029%

    No Known Activations