© 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. 5702
    Prev
    Next
    INDEX
    Explanations

    **within range**

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

    The neuron consistently fires on words that serve as section headings or titles, i.e. the first or prominent capitalized token that introduces a new part of the document.

    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
     desarrollar
    0.94
     criar
    0.93
     crear
    0.92
    ad
    0.88
    น่า
    0.86
    くる
    0.86
    h
    0.86
    b
    0.85
     analizar
    0.84
    няют
    0.84
    POSITIVE LOGITS
     uninsured
    0.68
    ieuses
    0.66
    elementReference
    0.65
     انواع
    0.63
     هنگام
    0.61
     Fantasy
    0.60
     молит
    0.59
    Newcastle
    0.59
    Married
    0.58
    Ger
    0.57
    Activations Density 0.001%

    No Known Activations