© 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. 87013
    Prev
    Next
    INDEX
    Explanations

    construct/craft

    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
    袿
    -1.88
    ཥ
    -1.77
    ꜆
    -1.73
    wendige
    -1.68
    
    -1.68
     incredi
    -1.66
    絎
    -1.64
    prove
    -1.64
    
    -1.63
     vitale
    -1.61
    POSITIVE LOGITS
     a
    2.84
     When
    1.96
     first
    1.90
     Since
    1.90
     so
    1.90
     an
    1.90
     You
    1.88
     We
    1.78
     This
    1.76
     had
    1.62
    Activations Density 0.025%

    No Known Activations