© 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. 89790
    Prev
    Next
    INDEX
    Explanations

    social work

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

    The neuron activates on mentions of social‐work and related human‐services terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    rops
    -0.79
    manufacturing
    -0.77
     ZF
    -0.75
     Maths
    -0.75
     mathematician
    -0.74
     PTFE
    -0.73
     substring
    -0.71
     mcd
    -0.71
     hormon
    -0.70
     moulding
    -0.70
    POSITIVE LOGITS
     social
    1.59
    Social
    1.34
    social
    1.22
     Social
    1.17
     clients
    1.10
     mezzo
    1.09
     NAS
    1.07
     MSW
    1.05
     practice
    1.02
    NAS
    1.00
    Activations Density 0.019%

    No Known Activations