© 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. 73824
    Prev
    Next
    INDEX
    Explanations

    legal or programming constructs

    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
     anadolu
    -0.84
     geométrico
    -0.84
    fifa
    -0.84
    abaikan
    -0.84
    Ajouter
    -0.84
     財布
    -0.82
     débats
    -0.79
    きましたが
    -0.79
     海外
    -0.77
    Création
    -0.77
    POSITIVE LOGITS
     total
    1.22
     count
    1.16
     last
    1.05
     history
    1.03
     time
    1.03
    ++;
    0.99
     statistics
    0.99
     record
    0.97
    ++;
    
    0.97
     cumulative
    0.95
    Activations Density 0.029%

    No Known Activations