© 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. 66362
    Prev
    Next
    INDEX
    Explanations

    psychological stability and security

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

    The neuron detects language giving health‐promotion advice or recommendations—especially mentions of health-promoting behaviors (e.g. during pregnancy).

    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
    featuring
    -1.18
    might
    -1.16
    Might
    -1.15
     garder
    -1.13
     тща
    -1.12
     longues
    -1.09
    obacz
    -1.05
    
    -1.05
    oneof
    -1.02
    opropyl
    -1.01
    POSITIVE LOGITS
     in
    1.56
     this
    1.27
     changes
    1.22
     at
    1.20
     with
    1.14
     using
    1.09
     after
    1.09
     because
    1.06
     related
    1.02
     includes
    1.01
    Activations Density 0.008%

    No Known Activations