© 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. 34-GEMMASCOPE-RES-131K
    4. 33262
    Prev
    Next
    INDEX
    Explanations

    XML includes and targets

    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
    -"+
    -0.99
     contoh
    -0.90
     censiti
    -0.90
     ""),
    -0.89
    czerw
    -0.88
    )";
    -0.87
    itieren
    -0.86
    UNI
    -0.86
    cartItem
    -0.85
    )";
    
    -0.84
    POSITIVE LOGITS
     plantea
    0.85
     разные
    0.81
     onCancelled
    0.80
    quences
    0.79
     festge
    0.77
     streamline
    0.77
    Acknowled
    0.77
    がたくさん
    0.77
    くださいね
    0.76
    顧問
    0.75
    Activations Density 0.003%

    No Known Activations