© 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. 49400
    Prev
    Next
    INDEX
    Explanations

    narrator/author reporting stories

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

    The neuron fires on meta-story and narrative markers—words that reference storytelling (e.g. tale, story, memoir, narrator, author, tells).

    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
     заявил
    -0.82
    恐怕
    -0.77
     zeggen
    -0.76
     szak
    -0.75
     murmurs
    -0.75
    anus
    -0.73
     Daarom
    -0.72
     yhte
    -0.72
    дия
    -0.72
    inition
    -0.72
    POSITIVE LOGITS
     relate
    4.34
     relates
    4.03
     relating
    3.67
     related
    3.63
    relate
    3.25
     recount
    3.02
    related
    2.95
     Related
    2.80
     relat
    2.80
    Related
    2.72
    Activations Density 0.092%

    No Known Activations