© 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. 6963
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and references

    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
    ckeys
    -0.81
     eindeutig
    -0.79
     fragrant
    -0.79
    のかもしれません
    -0.76
    echy
    -0.76
    funeralhome
    -0.76
     variability
    -0.75
    蜡
    -0.75
    гряз
    -0.73
    ffling
    -0.73
    POSITIVE LOGITS
    Mathematics
    1.05
     математи
    1.01
     Mathemat
    0.98
     generality
    0.98
     Mathematics
    0.96
     notation
    0.94
     Mathematical
    0.93
     Notation
    0.93
     matematika
    0.91
     mathematical
    0.88
    Activations Density 0.016%

    No Known Activations