© 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. 98085
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    wast
    -0.81
     Afric
    -0.74
    יטה
    -0.73
     aspetta
    -0.71
    izung
    -0.71
    hláš
    -0.71
     GPA
    -0.70
     unic
    -0.69
    twas
    -0.69
    ié
    -0.69
    POSITIVE LOGITS
     EF
    1.13
    EF
    1.10
    JOptionPane
    0.89
    agency
    0.87
     agency
    0.86
    Zo
    0.80
    wikipedia
    0.79
    عب
    0.79
    vertical
    0.76
     cães
    0.76
    Activations Density 0.007%

    No Known Activations