© 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. 38449
    Prev
    Next
    INDEX
    Explanations

    closing braces or code blocks

    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
    ();
    
    -0.90
    );
    
    -0.89
    ‐
    -0.87
    司
    -0.85
    (",");
    -0.85
    ]))
    -0.84
    »،
    -0.84
     ‘‘
    -0.82
    ">(</
    -0.81
     аккумуля
    -0.81
    POSITIVE LOGITS
    到这里
    1.03
    抜群
    0.97
     unprecedented
    0.93
     интел
    0.92
     drugie
    0.90
    达成
    0.90
    ilumin
    0.90
    出来ない
    0.90
     abusos
    0.89
     planète
    0.89
    Activations Density 0.104%

    No Known Activations