© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129022
    Prev
    Next
    INDEX
    Explanations

    reactive protein, divided by, Sichuan province

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

    geographical place names, particularly Chinese provinces and regions.

    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_10/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
    
    -3.16
    傒
    -2.84
    ꪔ
    -2.77
    祤
    -2.77
     This
    -2.70
    🛇
    -2.69
    ครื่อง
    -2.64
    ſſen
    -2.59
     剤
    -2.58
    ↵
    -2.53
    POSITIVE LOGITS
     laden
    2.56
    {
    2.45
    觏
    2.34
    `
    2.31
     
    2.27
     autres
    2.19
     I
    2.14
    ].
    2.08
     le
    2.08
    </td>
    2.06
    Activations Density 0.003%

    No Known Activations