© 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. 34953
    Prev
    Next
    INDEX
    Explanations

    telling stories

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

    This neuron detects personal storytelling cues—words and phrases that signal someone recounting their own experiences or anecdotes.

    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
    ヘル
    -0.75
    iol
    -0.74
     Summary
    -0.74
    órc
    -0.74
     简介
    -0.73
     ","
    -0.72
    掌握
    -0.72
    Summary
    -0.72
    ógio
    -0.71
    zió
    -0.71
    POSITIVE LOGITS
     stories
    5.00
    stories
    3.92
     story
    3.72
    Stories
    3.66
     Stories
    3.64
     anecdotes
    3.44
     tales
    3.41
     STORIES
    3.17
     anecdote
    3.11
     histórias
    2.70
    Activations Density 0.060%

    No Known Activations