© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    family related things

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

    The neuron detects mentions of “family” or family-oriented contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵
    -1.59
    の高い
    -1.44
    伋
    -1.42
     prostu
    -1.40
     pembeli
    -1.35
    *$
    -1.33
     hvordan
    -1.32
     THURSDAY
    -1.30
     cewek
    -1.30
     klient
    -1.28
    POSITIVE LOGITS
     family
    2.17
    family
    1.98
     Family
    1.76
    FAMIL
    1.55
     familia
    1.48
     ‘
    1.47
     FAMILY
    1.46
     família
    1.45
     famiglia
    1.45
    f
    1.38
    Activations Density 0.097%

    No Known Activations