© 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. 109170
    Prev
    Next
    INDEX
    Explanations

    point followed by specific terms

    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
     menjual
    -0.75
    ÜN
    -0.73
     martyrdom
    -0.72
    Cms
    -0.69
     Combine
    -0.69
    permutation
    -0.69
     firstName
    -0.67
     Treaty
    -0.67
     walkway
    -0.66
    страи
    -0.66
    POSITIVE LOGITS
     source
    0.91
    wise
    0.90
     fournisse
    0.82
    ródło
    0.80
     sources
    0.78
    ource
    0.77
    ensioni
    0.77
    getSource
    0.76
     cognitive
    0.75
    ikistan
    0.75
    Activations Density 0.039%

    No Known Activations