© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    what it

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

    The neuron fires on discourse markers that introduce explanations or reasoning (e.g. words in phrases like “the idea behind this”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases introducing explanations, qualifications, or comparisons of concepts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    expository, technical or instructional passages that explain concepts, present findings/comparisons, or offer recommendations.

    oai_token-act-pair · gpt-5Triggered 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
    timeline
    0.94
     Chairperson
    0.93
     timeline
    0.92
    Timeline
    0.92
     遊ん
    0.91
     ciudadanía
    0.90
     timelines
    0.88
    affiliated
    0.85
     kiddos
    0.85
    ксана
    0.84
    POSITIVE LOGITS
     použití
    1.24
    這種
    1.18
    这种
    1.17
     solche
    1.12
    此类
    1.07
    这类
    1.06
     이런
    1.05
     Verwendung
    1.05
     tohoto
    1.05
     lze
    1.04
    Activations Density 25.338%

    No Known Activations