© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41627
    Prev
    Next
    INDEX
    Explanations

    System.ComponentModel

    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
     myriad
    -1.98
     lauded
    -1.98
     famed
    -1.82
     decidedly
    -1.76
    archiwizowane
    -1.75
     pami
    -1.73
     vastly
    -1.73
     alcuni
    -1.71
     strikingly
    -1.70
    
    -1.70
    POSITIVE LOGITS
    These
    1.87
    ’
    1.77
    軼
    1.70
     at
    1.68
    This
    1.65
    隽
    1.59
    にほん
    1.52
     Martí
    1.51
     дов
    1.49
     stork
    1.48
    Activations Density 0.008%

    No Known Activations