© 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. 25795
    Prev
    Next
    INDEX
    Explanations

    referring to other people

    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
     now
    -1.05
     водитель
    -1.01
     sometimes
    -0.96
    如今
    -0.94
     you
    -0.94
     अब
    -0.91
    nict
    -0.90
    hancer
    -0.89
     sunsets
    -0.88
    常常
    -0.86
    POSITIVE LOGITS
     other
    1.84
     others
    1.76
     других
    1.55
     سایر
    1.45
     otros
    1.44
     다른
    1.42
     fellow
    1.37
    families
    1.37
     otras
    1.34
    autres
    1.34
    Activations Density 0.025%

    No Known Activations