© 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. 54148
    Prev
    Next
    INDEX
    Explanations

    German place names or words

    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
    があり
    -0.78
     Jake
    -0.76
    で
    -0.75
     reda
    -0.74
     川
    -0.74
     Nicholas
    -0.73
    NSNumber
    -0.73
    Ỗ
    -0.73
    が
    -0.73
    を
    -0.72
    POSITIVE LOGITS
    erty
    0.81
     bolj
    0.72
     Segmentation
    0.69
    すみません
    0.69
     mówią
    0.68
     unanim
    0.67
     echten
    0.67
    っぱり
    0.66
     území
    0.66
    🧱
    0.66
    Activations Density 0.028%

    No Known Activations