© 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. 70587
    Prev
    Next
    INDEX
    Explanations

    two-way communication and directional concepts

    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
    ↵
    -1.44
     In
    -1.38
      
    -1.35
     What
    -1.34
     she
    -1.33
     would
    -1.32
       
    -1.30
     F
    -1.30
         
    -1.29
           
    -1.29
    POSITIVE LOGITS
    紲
    1.87
    ꪔ
    1.82
    ayaquil
    1.75
     balení
    1.69
     systému
    1.69
    ጺ
    1.65
     SIMBAD
    1.61
    淠
    1.59
     peruano
    1.54
    鸯
    1.54
    Activations Density 0.024%

    No Known Activations