© 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. 118484
    Prev
    Next
    INDEX
    Explanations

    transition

    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
     جدول
    -0.83
    ieni
    -0.82
    柔ら
    -0.81
     viendra
    -0.80
     فنا
    -0.79
    ricus
    -0.78
    汆
    -0.77
     rook
    -0.77
    technologie
    -0.77
     trabajos
    -0.76
    POSITIVE LOGITS
     transition
    2.31
    transition
    1.95
     Transition
    1.91
    Transition
    1.88
     counter
    1.76
     transitional
    1.59
     transitions
    1.59
     fast
    1.58
     quick
    1.36
    counter
    1.35
    Activations Density 0.014%

    No Known Activations