© 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. 34-GEMMASCOPE-RES-131K
    7. 65534
    Prev
    Next
    INDEX
    Explanations

    engineer or engineering

    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_34/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
    Tourism
    -0.82
     Exter
    -0.75
    ärer
    -0.74
    شنامه
    -0.73
    retor
    -0.72
    ndal
    -0.71
     تصوير
    -0.71
     metabolites
    -0.71
    administ
    -0.70
    insee
    -0.69
    POSITIVE LOGITS
     engineering
    4.91
     engineers
    4.28
     engineer
    4.13
     Engineering
    3.98
    engineering
    3.75
     Engineers
    3.63
    Engineering
    3.56
     Engineer
    3.53
     ENGINEERING
    3.44
    engineer
    3.22
    Activations Density 0.117%

    No Known Activations