© 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. 23546
    Prev
    Next
    INDEX
    Explanations

    taxes and amounts

    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
    ָם
    -0.84
    нули
    -0.81
    勺
    -0.81
     emissions
    -0.79
    Desktop
    -0.79
    лиз
    -0.79
    第
    -0.78
     hearty
    -0.78
     HttpRequest
    -0.77
    tür
    -0.75
    POSITIVE LOGITS
    什么样的
    0.85
     cess
    0.84
     Rout
    0.84
     uter
    0.78
     Cess
    0.77
     applicable
    0.75
    どういう
    0.74
    そも
    0.74
     Demolition
    0.73
     conces
    0.72
    Activations Density 0.006%

    No Known Activations