© 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. 58471
    Prev
    Next
    INDEX
    Explanations

    equity investment firms

    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
     {
    -1.55
    In
    -1.51
    );
    -1.49
    e
    -1.46
    </td>
    -1.46
    es
    -1.45
    2
    -1.43
    p
    -1.42
     ות
    -1.41
    Ch
    -1.40
    POSITIVE LOGITS
     kertoo
    1.62
    
    1.60
    PHONY
    1.57
    
    1.57
    
    1.55
    鹚
    1.55
     mères
    1.54
     sentiers
    1.52
    necedor
    1.51
    cún
    1.48
    Activations Density 0.008%

    No Known Activations