© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130846
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find mentions of psychosocial care and support services.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    psychosocial support and care services

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

    This neuron identifies terms related to support services, including counseling, care, advisors, and health support programs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    éroport
    -1.19
    воло
    -1.13
     of
    -1.10
     celebró
    -1.07
    isling
    -1.06
    misen
    -1.04
     '*')
    -1.04
     meskipun
    -1.02
    iolis
    -1.00
    lesias
    -0.99
    POSITIVE LOGITS
     support
    1.69
     help
    1.61
     services
    1.52
     helping
    1.48
     helpful
    1.34
     wellness
    1.27
    nemers
    1.26
     providing
    1.24
     problemas
    1.22
     provide
    1.20
    Activations Density 0.040%

    No Known Activations