© 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. 23881
    Prev
    Next
    INDEX
    Explanations

    expresses understanding or lack thereof

    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
    streams
    -0.83
    pakan
    -0.82
    piecze
    -0.82
    rune
    -0.74
    gameOver
    -0.74
    туры
    -0.72
    llu
    -0.71
     yyl
    -0.71
    不知道
    -0.70
    kenn
    -0.69
    POSITIVE LOGITS
     understand
    7.78
     understanding
    7.56
     understood
    6.56
     understands
    6.41
     Understanding
    6.03
    understanding
    5.91
    Understanding
    5.84
     Understand
    5.47
    理解
    5.41
    understand
    5.41
    Activations Density 0.358%

    No Known Activations