© 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. 50467
    Prev
    Next
    INDEX
    Explanations

    protective cases and accessories

    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
    小さく
    -0.93
    imédia
    -0.78
    mones
    -0.77
    ueira
    -0.76
    emény
    -0.75
    יהם
    -0.74
     môn
    -0.73
    엌
    -0.71
    flats
    -0.71
    дые
    -0.71
    POSITIVE LOGITS
     case
    2.52
     cases
    2.30
     protective
    2.11
    Case
    2.00
     Case
    1.99
     Cases
    1.95
    Cases
    1.91
    protective
    1.88
    case
    1.88
    cases
    1.84
    Activations Density 0.031%

    No Known Activations