© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60579
    Prev
    Next
    INDEX
    Explanations

    mathematics and academic papers

    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
    ECTS
    -0.79
     Pleistocene
    -0.78
    dataset
    -0.76
     Initialized
    -0.75
    stanz
    -0.74
     النبي
    -0.74
     szolg
    -0.73
    Find
    -0.71
     pip
    -0.71
    timp
    -0.71
    POSITIVE LOGITS
     math
    0.98
     mathematics
    0.93
     Algebra
    0.86
     Math
    0.85
    Bull
    0.84
    اضی
    0.84
    math
    0.82
     maths
    0.81
     mathematicians
    0.81
     Bull
    0.78
    Activations Density 0.010%

    No Known Activations