© 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. 106510
    Prev
    Next
    INDEX
    Explanations

    conversation and talk

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

    The neuron strongly activates on words denoting conversational interaction (e.g. “conversation,” “texting,” “responding,” “chat,” “talk,” etc.).

    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
     furia
    -0.85
    niaus
    -0.84
     mengirimkan
    -0.79
     эмоции
    -0.76
     archivo
    -0.76
     CONTEM
    -0.76
    soka
    -0.76
    confer
    -0.75
     urg
    -0.74
    Interop
    -0.73
    POSITIVE LOGITS
     conversation
    3.20
    conversation
    2.34
     topics
    2.30
     conversational
    2.23
     Conversation
    2.19
    Conversation
    2.13
     conversations
    1.99
     conversación
    1.96
     topic
    1.91
     Gespräch
    1.91
    Activations Density 0.055%

    No Known Activations