© 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. 59113
    Prev
    Next
    INDEX
    Explanations

    GUI components and frameworks

    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
     linger
    -0.73
     through
    -0.73
     саду
    -0.72
     olmuş
    -0.72
     rinsed
    -0.71
     during
    -0.70
     blacksmith
    -0.70
    轍
    -0.69
     élément
    -0.69
    FirebaseUser
    -0.69
    POSITIVE LOGITS
     JFrame
    1.09
     hivyo
    0.89
     bút
    0.87
     такая
    0.87
    構築
    0.85
     window
    0.85
     manicura
    0.84
    JOptionPane
    0.83
    dialect
    0.82
     comisiones
    0.79
    Activations Density 0.003%

    No Known Activations