© 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. 22-GEMMASCOPE-RES-131K
    7. 73887
    Prev
    Next
    INDEX
    Explanations

    traffic flow and safety

    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_22/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
     –
    -2.78
    鲧
    -2.67
            
    -2.58
    т
    -2.44
    僂
    -2.42
     —
    -2.41
    ت
    -2.19
     Некоторые
    -2.16
                
    -2.14
    в
    -2.11
    POSITIVE LOGITS
    }
    2.80
    .
    2.53
     you
    2.22
    ⇰
    2.13
     Its
    2.09
    
    2.09
    飏
    2.08
     solches
    2.05
     quarre
    2.05
    
    2.03
    Activations Density 0.009%

    No Known Activations