© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9852
    Prev
    Next
    INDEX
    Explanations

    unlimited access or use

    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
     if
    -1.60
     to
    -1.47
     does
    -1.37
     about
    -1.34
        
    -1.34
           
    -1.30
            
    -1.28
     are
    -1.28
    Gilla
    -1.27
     precedenti
    -1.27
    POSITIVE LOGITS
    媗
    1.54
     exemplaires
    1.46
     voor
    1.46
    besos
    1.45
    狳
    1.42
     jejich
    1.37
    THING
    1.37
    
    1.36
     modèles
    1.33
    Thing
    1.32
    Activations Density 0.018%

    No Known Activations