© 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. 116731
    Prev
    Next
    INDEX
    Explanations

    success past

    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
     кем
    -0.85
    nikami
    -0.82
     ice
    -0.80
     Tahu
    -0.77
    轧
    -0.75
     pesos
    -0.75
     להת
    -0.75
     οικο
    -0.75
    íme
    -0.74
     recuerdos
    -0.74
    POSITIVE LOGITS
    문
    0.78
     kanyang
    0.77
     jumpsuit
    0.73
    Contact
    0.71
     contact
    0.71
    HB
    0.71
     Swaziland
    0.71
    去年
    0.70
    ATEUR
    0.69
    ઉ
    0.69
    Activations Density 0.011%

    No Known Activations