© 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. 55643
    Prev
    Next
    INDEX
    Explanations

    skilled immigration occupations checkpoints

    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
     campañas
    -0.77
     motif
    -0.76
    nend
    -0.74
    Etter
    -0.73
    mastered
    -0.71
     kohdetta
    -0.71
     кольца
    -0.71
    سع
    -0.71
     Rahim
    -0.71
    uhe
    -0.71
    POSITIVE LOGITS
     skilled
    1.70
     Skilled
    1.51
    skilled
    1.24
     skill
    1.13
     skills
    1.08
     immigration
    1.05
     immig
    1.05
     occupations
    1.03
     points
    1.00
     Skill
    0.92
    Activations Density 0.013%

    No Known Activations