© 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. 34530
    Prev
    Next
    INDEX
    Explanations

    condition then consequence

    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
    才行
    -1.10
    ябрь
    -1.07
     requiere
    -0.99
    的是
    -0.98
    都不知道
    -0.97
    也得
    -0.97
    都不能
    -0.97
     einzige
    -0.96
     tuttavia
    -0.96
     интерьере
    -0.93
    POSITIVE LOGITS
     just
    5.41
     then
    3.70
    就
    3.64
    ก็
    3.28
    Just
    3.25
    just
    2.89
     Just
    2.84
    就可以
    2.72
    าก็
    2.66
     就
    2.53
    Activations Density 0.003%

    No Known Activations