© 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. 107590
    Prev
    Next
    INDEX
    Explanations

    initialization and code elements

    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
    ᑐ
    -0.87
    respective
    -0.86
     nicolas
    -0.85
     autoridade
    -0.81
    pernicus
    -0.81
    ibilité
    -0.80
    ChatColor
    -0.79
     株式
    -0.79
    ക്ക
    -0.76
    というのも
    -0.75
    POSITIVE LOGITS
    init
    1.64
     init
    1.34
     Ленинград
    0.88
    INIT
    0.88
     نوج
    0.85
     jednak
    0.85
     van
    0.78
     none
    0.77
    self
    0.76
    deinit
    0.76
    Activations Density 0.010%

    No Known Activations