© 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. 14348
    Prev
    Next
    INDEX
    Explanations

    components/

    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
    '
    -1.95
    旆
    -1.88
    
    -1.86
    äge
    -1.84
     discer
    -1.81
     modifications
    -1.78
    可
    -1.78
    硨
    -1.77
    物
    -1.77
     provocó
    -1.75
    POSITIVE LOGITS
    𖥧
    2.42
     și
    2.33
     και
    2.30
        
    2.28
     और
    2.22
    というわけで
    2.20
    𝟭
    2.16
    珦
    2.08
            
    2.02
                   
    2.00
    Activations Density 0.031%

    No Known Activations