© 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. 13641
    Prev
    Next
    INDEX
    Explanations

    job careers employment

    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
     imposs
    -1.02
     apparence
    -1.02
    Wymiary
    -1.02
    ಆ
    -0.98
     varit
    -0.96
    ége
    -0.96
     сыром
    -0.96
     njego
    -0.96
    อร่อย
    -0.94
     ucc
    -0.94
    POSITIVE LOGITS
     after
    1.36
     после
    1.25
     após
    1.24
     industries
    1.23
     afterwards
    1.23
     employment
    1.21
     post
    1.17
     job
    1.15
     jobs
    1.13
     بعد
    1.13
    Activations Density 0.031%

    No Known Activations