© 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. 23616
    Prev
    Next
    INDEX
    Explanations

    Secret Service

    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
    🃏
    -0.92
     clinique
    -0.90
    Magyar
    -0.82
    átek
    -0.81
     Bounds
    -0.80
    iteln
    -0.80
     Kø
    -0.80
    노
    -0.79
    ıyoruz
    -0.79
     vong
    -0.79
    POSITIVE LOGITS
     состави
    1.00
    Sempre
    0.88
    少数
    0.81
    DetailComponent
    0.79
    鈎
    0.76
     coll
    0.76
    卸
    0.75
     Ebenso
    0.74
     richer
    0.73
    臨時
    0.73
    Activations Density 0.000%

    No Known Activations