© 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. 10-GEMMASCOPE-RES-131K
    7. 86749
    Prev
    Next
    INDEX
    Explanations

    bolded labels

    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
    ühungen
    -1.66
    '
    -1.66
     dejando
    -1.63
        
    -1.58
         
    -1.52
     Find
    -1.52
                
    -1.52
     [
    -1.50
     Always
    -1.50
     abbraccio
    -1.49
    POSITIVE LOGITS
    踅
    2.33
    槩
    2.16
    ᜀ
    2.03
    豋
    1.98
    蠵
    1.92
    鄠
    1.90
    Waktu
    1.87
     peluche
    1.84
    Redaktion
    1.83
     guerrero
    1.80
    Activations Density 0.001%

    No Known Activations