© 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. 104975
    Prev
    Next
    INDEX
    Explanations

    Android Activity

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "Activity" in Android code, particularly in class names and import statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    вать
    -2.36
    СКИ
    -2.16
     Если
    -2.13
     Есть
    -1.98
    是
    -1.97
    迅速
    -1.91
    完全
    -1.88
    цев
    -1.88
    ?"
    -1.85
    再
    -1.82
    POSITIVE LOGITS
    ↵↵
    2.42
    </td>
    2.39
    戆
    2.34
    }
    2.23
                                
    2.05
    </
    2.00
    涐
    2.00
                        
    1.99
     zmien
    1.95
    ²
    1.92
    Activations Density 0.002%

    No Known Activations