© 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. 55781
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and fractions

    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
     incontour
    -0.86
    춥
    -0.79
    Dip
    -0.77
     intenso
    -0.77
     bps
    -0.75
    Draws
    -0.75
    _();
    -0.75
    hik
    -0.75
     DRAW
    -0.75
     yl
    -0.74
    POSITIVE LOGITS
     兰
    0.92
     December
    0.82
     entries
    0.81
     changes
    0.75
     decimal
    0.75
     khususnya
    0.75
     penulis
    0.73
    erobe
    0.73
    artamento
    0.73
    èces
    0.71
    Activations Density 0.051%

    No Known Activations