© 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. 10-GEMMASCOPE-RES-131K
    7. 41352
    Prev
    Next
    INDEX
    Explanations

    sequences like 1-2, 1-nd, 1-gene

    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_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
    ........
    -2.16
    ・・・・・
    -2.14
    .......
    -2.13
     после
    -2.03
    フラワー
    -1.98
    .
    -1.94
    Surprisingly
    -1.94
    フォト
    -1.93
    Getting
    -1.91
     attain
    -1.91
    POSITIVE LOGITS
    脔
    2.33
     emisión
    2.08
     всѣ
    2.05
     奶茶
    2.05
    bluza
    1.98
    毉
    1.95
     koning
    1.95
    鉝
    1.94
    蠖
    1.93
     nieuwe
    1.91
    Activations Density 0.069%

    No Known Activations