© 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. 16013
    Prev
    Next
    INDEX
    Explanations

    local regional services

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

    The neuron is focusing on and strongly activating for salient content words or technical keywords (the main topic–bearing nouns) in the text.

    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
     fibrils
    0.95
     relato
    0.83
     puncture
    0.80
     conformational
    0.79
     demeanor
    0.75
     incarnations
    0.74
    牷
    0.73
     multiplets
    0.73
     maquill
    0.72
     allocator
    0.71
    POSITIVE LOGITS
    廃
    0.81
    RCT
    0.76
    honor
    0.72
    TRE
    0.72
    transparent
    0.71
    ت
    0.71
    ไม่
    0.71
    j
    0.70
    let
    0.70
    ed
    0.70
    Activations Density 0.000%

    No Known Activations