© 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. 10-GEMMASCOPE-RES-131K
    4. 12502
    Prev
    Next
    INDEX
    Explanations

    contact information (emails, phones)

    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_10/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
    });
    -2.27
    .”
    -1.92
     Weisheit
    -1.91
    ()){
    -1.77
     применя
    -1.73
    ());
    -1.73
    
    -1.72
    ?)
    -1.71
     they
    -1.68
    which
    -1.66
    POSITIVE LOGITS
     سپس
    1.94
     Then
    1.81
     เปิด
    1.78
     następnie
    1.73
    𝟴
    1.73
    graphique
    1.71
    月末
    1.67
    沺
    1.66
     バッグ
    1.66
     เป็น
    1.63
    Activations Density 0.025%

    No Known Activations