Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 476
    Prev
    Next
    INDEX
    Explanations

    over and over again

    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
     cambi
    -1.97
    氿
    -1.80
     perro
    -1.77
     dejamos
    -1.75
    {
    -1.74
    迨
    -1.72
    -1.70
     ponemos
    -1.65
     goo
    -1.58
    
    -1.58
    POSITIVE LOGITS
    ”
    1.95
    gencias
    1.91
    ,”
    1.81
    ńst
    1.77
    IBarButtonItem
    1.75
    \_\_
    1.73
     anlat
    1.70
    煇
    1.70
    </h3>
    1.70
    ном
    1.68
    Activations Density 0.003%

    No Known Activations