© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15961
    Prev
    Next
    INDEX
    Explanations

    superheroes and comic books

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

    This neuron fires on proper names of comic‐book characters or titles (e.g. superhero names and related character/title proper nouns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toscana
    0.62
    羊
    0.59
     bungal
    0.58
     Montessori
    0.57
     fermentation
    0.56
     ministre
    0.55
    民宿
    0.54
     kinh
    0.54
    馏
    0.53
    嬷
    0.53
    POSITIVE LOGITS
     superhero
    1.75
     Superhero
    1.70
    Superhero
    1.66
     superheroes
    1.55
     Superman
    1.54
    Marvel
    1.52
    Superman
    1.52
    Batman
    1.48
     Batman
    1.45
     Marvel
    1.44
    Activations Density 0.252%

    No Known Activations