© 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. 99756
    Prev
    Next
    INDEX
    Explanations

    "tang" in names, places, and medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "tang" in various contexts, whether as part of a proper noun, a standalone word, or part of longer words.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Garantía
    -0.84
    “……”
    -0.82
    嚴重
    -0.79
    Cell
    -0.78
     kait
    -0.77
     servire
    -0.76
    文學
    -0.75
    赶
    -0.75
    Pemer
    -0.75
     weiteres
    -0.75
    POSITIVE LOGITS
     Tang
    1.48
    Tang
    1.44
    tang
    1.41
     tang
    1.16
    entially
    1.14
     tangential
    1.04
     Tanger
    1.02
     TANG
    1.01
    ibles
    0.98
     Тан
    0.91
    Activations Density 0.011%

    No Known Activations