© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118686
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and imports

    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
     ilişk
    -0.86
     potrzeby
    -0.83
    ありますか
    -0.81
    Лі
    -0.78
    By
    -0.78
    ServiceModel
    -0.77
    EVT
    -0.76
    ený
    -0.76
    lst
    -0.76
     simply
    -0.76
    POSITIVE LOGITS
     {
    1.09
     uan
    0.91
     både
    0.90
     belles
    0.88
    aap
    0.88
     voyageurs
    0.85
    źdz
    0.83
     :{
    0.82
    っちり
    0.80
     fous
    0.79
    Activations Density 0.001%

    No Known Activations