© 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. 48339
    Prev
    Next
    INDEX
    Explanations

    UIAlerts and actions

    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
    Debut
    -0.88
     Debut
    -0.77
    ESSMENT
    -0.71
    épendant
    -0.71
     sterke
    -0.70
    Zara
    -0.64
    Fili
    -0.63
    취
    -0.63
     MessageBox
    -0.63
    Markus
    -0.62
    POSITIVE LOGITS
    Controller
    0.75
     厂
    0.73
     przec
    0.72
     No
    0.71
    ynthia
    0.70
     cumpli
    0.69
    več
    0.68
    WithMany
    0.68
    เฟ
    0.68
     running
    0.67
    Activations Density 0.056%

    No Known Activations