© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13540
    Prev
    Next
    INDEX
    Explanations

    descriptive appraisals after pauses

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

    The neuron fires on relatively content‐rich, informative words (key nouns, verbs, or adjectives) rather than on common function words or punctuation.

    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
     eventful
    0.77
     вновь
    0.75
    再次
    0.68
     Objectives
    0.66
    June
    0.65
    再び
    0.64
    煒
    0.64
    今日は
    0.63
    鋆
    0.62
     Classification
    0.61
    POSITIVE LOGITS
     zaten
    0.85
    거든요
    0.80
     진짜
    0.80
     necesitamos
    0.77
     Obamacare
    0.76
     jamais
    0.76
     ediyoruz
    0.73
     거고
    0.73
     nonprofits
    0.73
     kids
    0.70
    Activations Density 0.082%

    No Known Activations