© 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. 10-GEMMASCOPE-RES-131K
    7. 41891
    Prev
    Next
    INDEX
    Explanations

    job placement

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on words referring to placement or living arrangements—especially foster, care, placement, or living-with family contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    และ
    -1.38
     durant
    -1.31
     litri
    -1.30
     uye
    -1.22
     ISLAND
    -1.22
     correndo
    -1.16
     seks
    -1.16
     milioni
    -1.15
     milliard
    -1.15
    ↵
    -1.13
    POSITIVE LOGITS
     where
    1.79
     by
    1.48
     with
    1.32
     how
    1.26
    TRAD
    1.23
    鍙
    1.19
     freien
    1.18
     thier
    1.18
     damaligen
    1.17
     heighten
    1.16
    Activations Density 0.033%

    No Known Activations