© 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. 22-GEMMASCOPE-RES-131K
    7. 70506
    Prev
    Next
    INDEX
    Explanations

    recommendations and suggestions

    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_22/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
    ammlung
    -1.10
    gggg
    -1.04
     effekt
    -1.01
     ранее
    -0.99
     länder
    -0.98
    హ
    -0.98
    😶
    -0.96
     '-':
    -0.96
    tya
    -0.96
     risiko
    -0.95
    POSITIVE LOGITS
     your
    1.48
     через
    1.16
     try
    1.15
    わけではない
    1.05
     lantaran
    1.00
     megt
    0.99
     misschien
    0.94
     viszont
    0.94
     sites
    0.92
     forums
    0.92
    Activations Density 0.035%

    No Known Activations