© 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. 83330
    Prev
    Next
    INDEX
    Explanations

    child interactions and bonding

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

    The neuron detects mentions of the “parent–child interaction” concept (e.g. phrases about parent–child interactions and related opportunities).

    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
     پیر
    -0.89
    Señor
    -0.84
     planche
    -0.79
     młod
    -0.78
     adoles
    -0.78
     minors
    -0.77
     pencils
    -0.76
     шко
    -0.76
     Personas
    -0.75
     kids
    -0.73
    POSITIVE LOGITS
     interactions
    1.41
     interaction
    1.39
     play
    1.20
     Interaction
    1.20
     bonding
    1.19
     Interactions
    1.18
     interactive
    1.13
     interact
    1.13
     stimulation
    1.10
    Interaction
    1.08
    Activations Density 0.025%

    No Known Activations