© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8604
    Prev
    Next
    INDEX
    Explanations

    gaming, coins, diving, science, mistress

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

    The neuron responds to mentions of gaming- and gambling-related activities (e.g. games, arcades, casinos).

    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_24_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
    сного
    0.54
     Capabilities
    0.54
     Utilization
    0.51
    มอบ
    0.51
    গাঁ
    0.50
    多彩
    0.50
    🇮
    0.50
    ण
    0.49
    н
    0.49
    ة
    0.49
    POSITIVE LOGITS
     berhenti
    0.62
     lair
    0.61
     любят
    0.59
     unscrupulous
    0.59
     addictions
    0.58
     aren
    0.56
     salari
    0.56
     DJs
    0.56
     barons
    0.56
     estão
    0.55
    Activations Density 0.014%

    No Known Activations