© 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. 11899
    Prev
    Next
    INDEX
    Explanations

    listening to understand needs

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

    The neuron detects promotional service‐offer language, especially first‐person (“we” or “I”) statements promising or describing what the provider will do.

    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
    遴
    -0.88
    anmar
    -0.80
     DECISION
    -0.80
     reflexiones
    -0.76
    ujących
    -0.73
    رفته
    -0.73
    comparing
    -0.73
    なきゃ
    -0.73
    junctive
    -0.73
     اقدام
    -0.73
    POSITIVE LOGITS
     listen
    2.31
     listening
    2.16
     listens
    2.14
     listened
    2.13
     understand
    1.91
     understanding
    1.80
     Listen
    1.76
    了解
    1.74
     LISTEN
    1.72
    listen
    1.71
    Activations Density 0.038%

    No Known Activations