© 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. 34-GEMMASCOPE-RES-131K
    7. 1871
    Prev
    Next
    INDEX
    Explanations

    having conversations

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

    the neuron detects mentions of “life” in the context of end-of-life or life-expectancy discussions.

    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
     Må
    -0.74
    enfance
    -0.71
    Commentary
    -0.69
     Heiz
    -0.69
     RECOMM
    -0.69
     sona
    -0.67
     WEDDING
    -0.67
     SUPREME
    -0.66
     divisible
    -0.66
    Trabajo
    -0.66
    POSITIVE LOGITS
     conversation
    3.61
     conversations
    3.52
     Conversations
    2.72
    conversation
    2.69
    Conversation
    2.58
     Conversation
    2.48
     conversación
    2.42
     conversaciones
    2.41
    conversations
    2.39
     having
    2.36
    Activations Density 0.042%

    No Known Activations