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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64706
    Prev
    Next
    INDEX
    Explanations

    seed context

    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
    信頼
    -0.79
     herd
    -0.77
    ناسب
    -0.75
    ངས་
    -0.75
    inado
    -0.74
    opher
    -0.74
    jącym
    -0.73
     Staging
    -0.73
    割合
    -0.70
     Vol
    -0.70
    POSITIVE LOGITS
    Seed
    1.09
     Seed
    0.95
     seed
    0.95
     chronological
    0.82
    Seeder
    0.81
    сей
    0.80
     cili
    0.80
    eseed
    0.79
    zów
    0.77
     Seeder
    0.77
    Activations Density 0.009%

    No Known Activations