© 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. 103927
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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
    有意
    -0.85
    essive
    -0.81
    iremos
    -0.77
     feces
    -0.77
    salut
    -0.75
     faudra
    -0.74
    BIM
    -0.73
     herren
    -0.72
    логи
    -0.72
    fvar
    -0.72
    POSITIVE LOGITS
    hour
    0.79
    license
    0.79
     sumpay
    0.78
     федера
    0.77
    tern
    0.77
     sql
    0.76
     tohto
    0.76
     ancak
    0.75
    field
    0.75
    core
    0.75
    Activations Density 0.002%

    No Known Activations