© 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. 90528
    Prev
    Next
    INDEX
    Explanations

    growing up

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

    The neuron fires on mentions of television-related content—TV, channels, show titles, and associated nostalgia or viewing experiences.

    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
     बच्
    -0.85
    ությ
    -0.84
    赤ちゃん
    -0.81
    ='';
    -0.79
     ambayo
    -0.77
     tū
    -0.77
     Francus
    -0.75
     コード
    -0.74
     barne
    -0.73
    ortunadamente
    -0.72
    POSITIVE LOGITS
     growing
    6.41
    Growing
    5.16
    growing
    5.03
     Growing
    4.91
     grew
    2.94
     GROW
    2.91
     crecer
    2.56
     creciendo
    2.55
     grow
    2.55
     grows
    2.48
    Activations Density 0.081%

    No Known Activations