© 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. 22-GEMMASCOPE-RES-131K
    7. 130494
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on hyperbolic, promotional superlatives and emphatic claims (e.g. “the greatest story ever told,” “reads like a novel”) typical of book‐blurb hype.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    narrativestoryhistory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    edade
    -1.05
    fifa
    -1.01
     are
    -1.01
     войска
    -1.00
     use
    -0.98
    劫
    -0.94
    傅
    -0.93
    辨
    -0.93
     apply
    -0.92
     бла
    -0.90
    POSITIVE LOGITS
     events
    1.55
     history
    1.52
     story
    1.39
     narrative
    1.30
    istory
    1.30
     stories
    1.27
     chapters
    1.22
     racconto
    1.19
    events
    1.17
     désolés
    1.17
    Activations Density 0.085%

    No Known Activations