© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1691
    Prev
    Next
    INDEX
    Explanations

    what questions seeking explanation

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

    This neuron detects the presence of interrogative Cue words—especially “what”—marking the start of a question.

    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
    alians
    -0.95
     ARISING
    -0.92
    helps
    -0.91
     ofrece
    -0.88
    offers
    -0.87
    shows
    -0.86
    IBILITY
    -0.86
    리를
    -0.85
    findViewById
    -0.85
    jde
    -0.84
    POSITIVE LOGITS
     caused
    1.62
     causes
    1.55
     causing
    1.37
     gave
    1.22
     cause
    1.20
     drove
    1.19
     led
    1.19
     makes
    1.12
     happened
    1.11
     made
    1.09
    Activations Density 0.051%

    No Known Activations