© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79534
    Prev
    Next
    INDEX
    Explanations

    dependent :destroy / onDelete

    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_22/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
     πρ
    -1.16
    ﹍﹍
    -1.11
    鸶
    -1.11
    穑
    -1.11
    PRIVACY
    -1.11
    猡
    -1.06
    ࿆
    -1.06
     doccia
    -1.06
     acciaio
    -1.05
    ोर्ट
    -1.05
    POSITIVE LOGITS
     például
    1.10
     یا
    1.09
     amikor
    0.96
    If
    0.95
     caseros
    0.94
    ロイ
    0.94
    when
    0.94
    Give
    0.93
    موت
    0.93
     чому
    0.93
    Activations Density 0.002%

    No Known Activations