© 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. 80982
    Prev
    Next
    INDEX
    Explanations

    arrow or @ prefix

    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
     допол
    -0.75
    usi
    -0.72
     Scheme
    -0.71
    pping
    -0.69
    beur
    -0.67
     Resurrection
    -0.67
     mỡ
    -0.67
     pronouncing
    -0.65
    vete
    -0.65
     sling
    -0.64
    POSITIVE LOGITS
    Calvin
    0.66
    StatusBar
    0.64
     interact
    0.63
    vastatin
    0.63
     Garza
    0.62
     NATIONS
    0.62
    StatusCodes
    0.61
     Oaks
    0.61
     فناوری
    0.60
    江南
    0.59
    Activations Density 0.066%

    No Known Activations