© 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. 575
    Prev
    Next
    INDEX
    Explanations

    stepper motors

    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
    〼
    -2.20
     所以
    -2.02
    ようになる
    -1.87
     收納
    -1.82
    ቷ
    -1.80
    剮
    -1.79
     breite
    -1.78
     chil
    -1.78
     tue
    -1.76
    老爷
    -1.75
    POSITIVE LOGITS
    푙
    2.50
     onCreateView
    2.47
    珦
    2.45
    ጺ
    2.39
    
    2.36
    ᚔ
    2.31
    ﱠ
    2.30
    
    2.30
    咴
    2.28
    ྄
    2.25
    Activations Density 0.010%

    No Known Activations