© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83210
    Prev
    Next
    INDEX
    Explanations

    message

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

    The neuron activates on words signaling communications or alerts—especially terms like “message” or “warning.”

    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
    çası
    -0.91
    mentos
    -0.82
    reuth
    -0.76
     teléfono
    -0.76
    Tutto
    -0.75
     swore
    -0.74
    ত্র
    -0.74
    δη
    -0.74
    ása
    -0.73
    ConnectionState
    -0.73
    POSITIVE LOGITS
     message
    6.56
    message
    5.06
     messages
    4.75
     Message
    4.38
    Message
    4.22
    MESSAGE
    3.98
     MESSAGE
    3.84
     mensaje
    3.78
     msg
    3.59
     mesaj
    3.48
    Activations Density 0.045%

    No Known Activations