© 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. 110846
    Prev
    Next
    INDEX
    Explanations

    float and floating-point numbers

    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
     Fortunately
    -1.02
     Luckily
    -0.94
     Incidentally
    -0.91
     exactamente
    -0.90
     Thankfully
    -0.89
    swagger
    -0.89
     vettor
    -0.88
    ণ
    -0.88
    𝑬
    -0.87
     появились
    -0.85
    POSITIVE LOGITS
     Float
    1.58
     float
    1.31
     Flo
    1.27
     Floating
    1.19
     FLOAT
    1.09
    Float
    1.09
     CascadeType
    1.05
    𓋼
    1.05
    parseFloat
    1.05
     floats
    1.03
    Activations Density 0.007%

    No Known Activations