© 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. 103883
    Prev
    Next
    INDEX
    Explanations

    vocational and technical training

    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
    сумка
    -0.83
     paci
    -0.79
    cubo
    -0.78
    értel
    -0.75
    hecho
    -0.75
     literary
    -0.74
    Latency
    -0.73
    Kamu
    -0.73
    écrire
    -0.73
     kancel
    -0.72
    POSITIVE LOGITS
     vocational
    2.73
     Vocational
    2.22
    Voc
    1.66
    voc
    1.56
     Beruf
    1.43
     CTE
    1.41
     technical
    1.40
     VET
    1.39
     trades
    1.34
     skills
    1.32
    Activations Density 0.022%

    No Known Activations