© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101877
    Prev
    Next
    INDEX
    Explanations

    making an announcement

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

    The neuron activates on announcement language, especially tokens like “announce,” “announced,” or announcement headings.

    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
     في
    -2.45
     Problemen
    -2.30
    )
    -2.27
    2
    -2.16
    5
    -1.97
     In
    -1.97
    3
    -1.91
    6
    -1.85
     -
    -1.82
     recently
    -1.81
    POSITIVE LOGITS
    Ꮉ
    2.88
    柃
    2.42
    彀
    2.42
    鶿
    2.30
    ꪔ
    2.30
    
    2.25
    涑
    2.19
    ︳
    2.19
    
    2.17
    ↵
    2.16
    Activations Density 0.009%

    No Known Activations