© 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. 59172
    Prev
    Next
    INDEX
    Explanations

    .pdf

    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
     top
    -0.71
    Wrestling
    -0.69
     SRP
    -0.67
    Symfony
    -0.66
     Wrestling
    -0.65
     Dab
    -0.65
    Flatten
    -0.65
    utils
    -0.65
     wrestling
    -0.65
     мет
    -0.64
    POSITIVE LOGITS
    Usos
    0.71
    Чтоб
    0.68
     দে
    0.66
     zien
    0.65
     realizará
    0.64
    massive
    0.64
    eam
    0.63
     Kochen
    0.63
    Installed
    0.63
     gorą
    0.62
    Activations Density 0.076%

    No Known Activations