© 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. 84583
    Prev
    Next
    INDEX
    Explanations

    grams of protein, carbs

    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
    importance
    -0.87
     energy
    -0.87
     енер
    -0.85
     Thousands
    -0.85
    頴
    -0.77
     membahas
    -0.76
     meningkat
    -0.75
    現貨
    -0.73
    vfs
    -0.72
     sabbath
    -0.72
    POSITIVE LOGITS
     grams
    1.27
    grams
    1.08
    Boom
    0.92
    PTT
    0.77
    に対
    0.76
     net
    0.75
    วน
    0.75
     tõ
    0.75
     Boom
    0.75
    omg
    0.74
    Activations Density 0.012%

    No Known Activations