© 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. 63338
    Prev
    Next
    INDEX
    Explanations

    stories and telling

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

    This neuron fires strongly on bibliographic citation strings—especially the parentheses, hyphens, page numbers, years, and punctuation that appear in reference entries.

    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
    莖
    -0.83
     موسیقی
    -0.82
     отметил
    -0.80
     Deum
    -0.77
     فہرست
    -0.75
     reformers
    -0.74
     chào
    -0.73
     πλη
    -0.71
     ов
    -0.69
     музыку
    -0.69
    POSITIVE LOGITS
     storytelling
    3.53
     storyteller
    3.34
     stories
    3.22
     story
    3.05
    stories
    2.89
    story
    2.75
     telling
    2.72
     Storytelling
    2.70
    Story
    2.58
     teller
    2.55
    Activations Density 0.063%

    No Known Activations