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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48495
    Prev
    Next
    INDEX
    Explanations

    category or categories

    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
    demir
    -0.91
    udière
    -0.78
    зировать
    -0.77
    siana
    -0.73
     掃除
    -0.72
     故事
    -0.72
    version
    -0.71
     versión
    -0.69
     camas
    -0.69
     marido
    -0.67
    POSITIVE LOGITS
     category
    2.52
     categories
    2.41
     Category
    1.74
    category
    1.73
     classification
    1.70
    Category
    1.64
    getCategory
    1.63
     getCategory
    1.55
     genre
    1.52
     catégories
    1.52
    Activations Density 0.029%

    No Known Activations