© 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. 4810
    Prev
    Next
    INDEX
    Explanations

    true or swapped

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

    The neuron is picking out the most content-bearing (high tf–idf) words in each passage (i.e. the rare or key nouns and verbs).

    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
     mudança
    0.84
     rischio
    0.81
    antically
    0.77
    ਼
    0.76
     distributional
    0.75
     kēia
    0.74
     currentTime
    0.71
    ों
    0.71
     वेळी
    0.70
    цеп
    0.70
    POSITIVE LOGITS
    营造
    0.77
    IND
    0.74
    PROGRESS
    0.73
    ENG
    0.72
    Ю
    0.72
    鼹
    0.71
    有机
    0.71
    也会
    0.70
    NO
    0.70
    Silva
    0.70
    Activations Density 0.001%

    No Known Activations