© 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. 78273
    Prev
    Next
    INDEX
    Explanations

    comic book superheroes and teams

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

    The neuron is detecting named entities—proper nouns, titles, and numeric tokens.

    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
    Godzilla
    -0.74
    LineNumber
    -0.73
     Godzilla
    -0.73
    Epidemiology
    -0.73
     Infected
    -0.73
     BRITAIN
    -0.71
    Rég
    -0.71
     Analyses
    -0.71
     Polymers
    -0.70
     Coldplay
    -0.68
    POSITIVE LOGITS
     Marvel
    1.17
     comics
    1.08
     comic
    1.03
    Marvel
    0.92
    comics
    0.82
    comic
    0.81
     Comics
    0.77
    etag
    0.77
     rice
    0.76
     Series
    0.75
    Activations Density 0.009%

    No Known Activations