© 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. 115744
    Prev
    Next
    INDEX
    Explanations

    children and their ages

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

    The neuron detects references to family or household members (e.g. kids, children, pets, families, others).

    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
     for
    -1.20
     on
    -1.03
     in
    -0.90
     hänen
    -0.85
     itself
    -0.84
     प्रयास
    -0.82
     contains
    -0.82
    𝕣
    -0.81
     begegnen
    -0.81
     From
    -0.81
    POSITIVE LOGITS
    whom
    1.42
     ages
    1.42
     whom
    1.41
     who
    1.21
     quienes
    1.12
     которых
    1.09
    orous
    1.09
     vacunas
    1.05
     themselves
    1.03
     colorir
    1.01
    Activations Density 0.031%

    No Known Activations