© 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. 119417
    Prev
    Next
    INDEX
    Explanations

    content warnings and legal contexts

    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
    atorics
    -0.87
     étanche
    -0.83
     x
    -0.82
    chenen
    -0.82
    setX
    -0.80
    noteq
    -0.79
     შ
    -0.78
    ஈ
    -0.76
    ן
    -0.76
     X
    -0.76
    POSITIVE LOGITS
     برخی
    0.95
     conqu
    0.92
     fleeting
    0.91
     scenes
    0.88
     brief
    0.88
     thematic
    0.87
     BRIEF
    0.87
     temi
    0.87
     بعض
    0.86
     CONSTANT
    0.85
    Activations Density 0.015%

    No Known Activations