© 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. 103476
    Prev
    Next
    INDEX
    Explanations

    asking questions

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

    This neuron fires on numeric labels and headings (e.g. question numbers, list indices, or other standalone numbers) in the document.

    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
    themselves
    -1.19
    himself
    -1.13
    vertissement
    -1.01
     Liège
    -1.00
     pantal
    -0.98
     Obispo
    -0.97
     kehamilan
    -0.97
     vnder
    -0.95
     रि
    -0.95
     grup
    -0.94
    POSITIVE LOGITS
     what
    2.89
     who
    2.23
     describe
    2.02
     favorite
    1.95
     What
    1.79
     if
    1.76
     tell
    1.71
     Describe
    1.70
     which
    1.69
     favourite
    1.66
    Activations Density 0.009%

    No Known Activations