© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 282
    Prev
    Next
    INDEX
    Explanations

    email subjects and addresses

    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
     {;
    -0.79
     through
    -0.77
    вной
    -0.75
    )();
    -0.75
     mengalir
    -0.75
    regelen
    -0.74
     Küste
    -0.74
     apapun
    -0.74
     whose
    -0.73
    kungan
    -0.73
    POSITIVE LOGITS
     شاهد
    0.85
    phylococcus
    0.83
    etje
    0.82
     horrid
    0.80
     inserire
    0.80
     Villanueva
    0.78
    ตรี
    0.76
    מוס
    0.75
    חי
    0.75
     例
    0.75
    Activations Density 0.002%

    No Known Activations