© 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. 15697
    Prev
    Next
    INDEX
    Explanations

    perceived future

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

    The neuron fires strongly on the very first content word at the start of each new paragraph or text block.

    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
    ન
    0.78
    う
    0.78
    World
    0.78
     chút
    0.76
     luxuries
    0.76
    雫
    0.75
     metros
    0.74
    RAM
    0.73
    RA
    0.73
     Hospitality
    0.73
    POSITIVE LOGITS
    ן
    0.78
    ʰ
    0.75
     څرنګ
    0.74
    lessly
    0.73
    
    0.73
    yeh
    0.73
     тебя
    0.72
     underwent
    0.72
    녜
    0.71
    laş
    0.71
    Activations Density 0.000%

    No Known Activations