© 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. 10968
    Prev
    Next
    INDEX
    Explanations

    configuration and sequence markers

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

    This neuron responds to domain‐style tokens and other short uppercase/acronym-like strings (e.g. “.com,” “.org,” “PDF,” “COPYRIGHT,” “IMAGES,” etc.).

    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
    我要
    0.70
    要
    0.64
    astia
    0.64
    em
    0.64
    採用
    0.64
    使
    0.62
     alimentation
    0.61
    以
    0.61
    にかく
    0.60
    bet
    0.60
    POSITIVE LOGITS
     antiguo
    0.90
     jugadores
    0.88
     extranjero
    0.88
     direcciones
    0.88
    
    0.88
     økonom
    0.87
     viernes
    0.86
    티브
    0.85
     jugador
    0.84
    ჲ
    0.82
    Activations Density 0.003%

    No Known Activations