© 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. 55761
    Prev
    Next
    INDEX
    Explanations

    summation and totals

    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
     clínicos
    -0.84
     đón
    -0.79
     pygame
    -0.78
    actual
    -0.78
     haben
    -0.78
    rated
    -0.77
    spread
    -0.75
    俎
    -0.75
    úmero
    -0.75
    turn
    -0.74
    POSITIVE LOGITS
     totals
    2.11
    Totals
    2.02
     grand
    1.98
    TOTAL
    1.98
     Totals
    1.97
     subtotal
    1.87
    Subtotal
    1.72
     Grand
    1.59
    grand
    1.57
    Grand
    1.54
    Activations Density 0.012%

    No Known Activations