© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91395
    Prev
    Next
    INDEX
    Explanations

    code ending punctuation

    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
    JOptionPane
    -1.09
     alerted
    -1.06
     alert
    -1.02
     alerts
    -0.98
    Signals
    -0.93
    MessageBox
    -0.92
    Toast
    -0.90
     alerting
    -0.86
    alert
    -0.86
     Alert
    -0.85
    POSITIVE LOGITS
    DeleteBehavior
    0.92
     begyn
    0.85
     eventually
    0.84
    菜單
    0.84
    بوط
    0.84
    百分之
    0.82
    vän
    0.81
     mechanically
    0.81
    łości
    0.81
    eventually
    0.80
    Activations Density 0.028%

    No Known Activations