© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 637
    Prev
    Next
    INDEX
    Explanations

    separation and isolation

    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
    .
    -1.85
         
    -1.33
    ₹
    -1.30
    harap
    -1.27
          
    -1.26
       
    -1.26
    acebook
    -1.26
    ˂
    -1.26
     Such
    -1.23
     deserted
    -1.23
    POSITIVE LOGITS
    ;&
    1.45
     completamente
    1.45
     名片
    1.39
    앙
    1.39
     大きい
    1.38
    ぞれ
    1.37
     diferite
    1.36
    harapkan
    1.36
     seperate
    1.34
     separately
    1.34
    Activations Density 0.039%

    No Known Activations