© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102554
    Prev
    Next
    INDEX
    Explanations

    error, exception, or security 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
     ventri
    -0.70
    틸
    -0.69
    ランプ
    -0.69
     ports
    -0.68
     pinn
    -0.67
     Luci
    -0.67
     phono
    -0.67
     fluctu
    -0.67
     криста
    -0.67
     nhận
    -0.66
    POSITIVE LOGITS
     natürlich
    0.79
    ственных
    0.77
     typu
    0.76
    ITÀ
    0.74
     типа
    0.71
     Duke
    0.71
     тюрь
    0.70
     جشن
    0.68
     malah
    0.68
    psis
    0.68
    Activations Density 0.038%

    No Known Activations