© 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. 101449
    Prev
    Next
    INDEX
    Explanations

    pairs connected by and/or to

    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
     they
    -1.79
    </strong>
    -1.67
    
    -1.52
    
    -1.44
     pensó
    -1.43
    hidupan
    -1.42
    ükü
    -1.41
    tranh
    -1.41
    oof
    -1.40
     Các
    -1.39
    POSITIVE LOGITS
     convaincre
    1.49
     one
    1.44
     that
    1.42
     stava
    1.42
     設計
    1.41
    Although
    1.38
     gewünschten
    1.37
     psicologia
    1.35
    ⚐
    1.34
     aforesaid
    1.32
    Activations Density 0.073%

    No Known Activations