© 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. 92605
    Prev
    Next
    INDEX
    Explanations

    javascript alert

    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
    祈り
    -0.80
    namese
    -0.77
    ボディ
    -0.74
    埂
    -0.73
    روسية
    -0.73
    琅
    -0.73
    rs
    -0.72
     są
    -0.71
    囲
    -0.71
    馴染
    -0.71
    POSITIVE LOGITS
    alert
    1.16
    Please
    1.07
    ("
    1.05
     alert
    1.02
     solicita
    0.99
     Alert
    0.99
     demokra
    0.98
     JOptionPane
    0.94
    please
    0.94
    SystemColors
    0.93
    Activations Density 0.006%

    No Known Activations