© 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. 118062
    Prev
    Next
    INDEX
    Explanations

    fundamental constants and physics calculations

    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
    唄
    -0.85
     Cables
    -0.76
    zont
    -0.75
    ブ
    -0.73
    setEnabled
    -0.69
    lictions
    -0.69
    reur
    -0.68
    "@
    -0.67
     oligonucleotide
    -0.66
    ховик
    -0.66
    POSITIVE LOGITS
     constantes
    1.54
     constants
    1.54
     Constants
    1.39
    constants
    1.27
    Constants
    1.15
     constante
    1.13
     constant
    1.13
     conversion
    1.05
     Const
    1.03
     ثابت
    1.03
    Activations Density 0.024%

    No Known Activations