© 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. 37841
    Prev
    Next
    INDEX
    Explanations

    describing attributes or characteristics

    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
    惕
    -0.82
     desenhos
    -0.82
     fanden
    -0.78
    ̓
    -0.77
     Wiktionnaire
    -0.77
     gewesen
    -0.77
     paisajes
    -0.77
     Messung
    -0.76
    estion
    -0.75
    TextUtils
    -0.75
    POSITIVE LOGITS
     distinguished
    1.03
     perfectly
    1.02
     significantly
    1.02
     successfully
    0.96
     differ
    0.95
     Differ
    0.94
     differs
    0.93
     belongs
    0.91
     memiliki
    0.91
     endowed
    0.90
    Activations Density 0.025%

    No Known Activations