© 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. 6170
    Prev
    Next
    INDEX
    Explanations

    future trends and potential

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

    The neuron detects occurrences of the word “future.”

    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
     sedative
    1.19
    Сер
    1.13
    ⺆
    1.13
     Andover
    1.12
    ంథ
    1.11
    ены
    1.08
     meningitis
    1.06
    ྜ
    1.05
     semisimple
    1.05
    к
    1.05
    POSITIVE LOGITS
     поколения
    1.09
    future
    1.04
     FUTURE
    1.04
    of
    1.02
     mendatang
    1.02
     futuras
    0.99
     future
    0.99
     generations
    0.98
    FUTURE
    0.97
     generaciones
    0.97
    Activations Density 0.082%

    No Known Activations