© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11000
    Prev
    Next
    INDEX
    Explanations

    filler list

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

    This neuron detects capitalized named entities—proper names, titles, anniversaries, and similar multiword name-like phrases.

    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
     facilitators
    0.64
     drama
    0.63
    Categorie
    0.62
     détecter
    0.60
    剧中
    0.60
    戲
    0.59
     menonton
    0.59
     Drama
    0.59
    drama
    0.58
     bollywood
    0.58
    POSITIVE LOGITS
     prequel
    1.02
     sequel
    0.96
     continuity
    0.91
     sequels
    0.89
    continuity
    0.85
    延续
    0.83
     revisit
    0.82
     fanbase
    0.81
     fans
    0.79
    续
    0.79
    Activations Density 0.380%

    No Known Activations