© 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. 6687
    Prev
    Next
    INDEX
    Explanations

    stay tuned

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

    This neuron detects teaser or suspense phrases that prompt the reader to “stay tuned” for upcoming content or announcements.

    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
    괜
    -0.85
    
    -0.82
     szcze
    -0.75
     verres
    -0.74
     cérami
    -0.73
    しくない
    -0.73
    isOk
    -0.73
    状態で
    -0.72
    årige
    -0.72
     klima
    -0.71
    POSITIVE LOGITS
     stay
    5.69
    Stay
    5.00
     Stay
    4.88
    stay
    4.34
     stays
    3.64
     stayed
    3.63
     STAY
    3.42
    STAY
    3.00
    Stayed
    2.83
     staying
    2.52
    Activations Density 0.060%

    No Known Activations