© 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. 117954
    Prev
    Next
    INDEX
    Explanations

    corporate office and jobs

    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
     leng
    -0.86
     ngu
    -0.85
    Lengths
    -0.84
     cipolla
    -0.83
    fél
    -0.83
    cycline
    -0.80
    pherd
    -0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.79
     pectoral
    -0.77
     menores
    -0.76
    POSITIVE LOGITS
     corporate
    3.69
    Corporate
    2.91
     Corporate
    2.77
    corporate
    2.72
     CORPOR
    2.13
     корпора
    2.05
     corpor
    1.88
    CORPOR
    1.73
     office
    1.64
     corporations
    1.63
    Activations Density 0.052%

    No Known Activations