© 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. 10-GEMMASCOPE-RES-131K
    7. 105614
    Prev
    Next
    INDEX
    Explanations

    two different ways

    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_10/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
     its
    -1.71
     formerly
    -1.61
    年来
    -1.60
     նաև
    -1.55
     質
    -1.53
    
    -1.52
    なかった
    -1.48
     already
    -1.47
     is
    -1.45
     wszyst
    -1.44
    POSITIVE LOGITS
    讪
    1.55
     $
    1.42
    ↵
    1.38
    хіво
    1.34
     και
    1.32
    これで
    1.32
    grao
    1.31
     tedy
    1.30
     použití
    1.28
     interpreta
    1.27
    Activations Density 0.047%

    No Known Activations