© 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. 10-GEMMASCOPE-RES-131K
    7. 12920
    Prev
    Next
    INDEX
    Explanations

    assembly registers and code comments

    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
    𝘼
    -1.65
    
    -1.50
     erhöht
    -1.48
    
    -1.48
    WSER
    -1.47
     één
    -1.46
    MLElement
    -1.46
     Что
    -1.46
     triliun
    -1.45
    adrez
    -1.45
    POSITIVE LOGITS
    .
    1.50
     went
    1.38
     kwiet
    1.35
    </h3>
    1.34
     even
    1.26
    贅
    1.24
    tava
    1.23
    le
    1.23
     SOBRE
    1.23
     talked
    1.21
    Activations Density 0.006%

    No Known Activations