© 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. 11792
    Prev
    Next
    INDEX
    Explanations

    phrasing conditional questions

    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
    );
    -1.57
    ſſen
    -1.57
    その
    -1.52
     многих
    -1.51
     decorados
    -1.50
     такие
    -1.36
     quite
    -1.34
    となり
    -1.31
    ところ
    -1.28
     всем
    -1.28
    POSITIVE LOGITS
     {
    
    
    1.70
    鹮
    1.56
    差不多
    1.48
    existsSync
    1.48
    可不
    1.44
    也得
    1.44
    讥
    1.43
    能在
    1.42
     because
    1.42
    痦
    1.40
    Activations Density 0.015%

    No Known Activations