© 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. 5477
    Prev
    Next
    INDEX
    Explanations

    complex and nuanced topics

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

    The neuron responds to substantive content words (especially descriptive adjectives and nouns) that carry strong semantic weight.

    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
    墓志
    0.66
    勺
    0.63
    Ecco
    0.63
     〢
    0.62
    ăzi
    0.61
    STIT
    0.60
    HTMLElement
    0.59
    ぴ
    0.59
     পরিচ
    0.57
    𝓈
    0.57
    POSITIVE LOGITS
     confines
    0.87
     intricacies
    0.81
     ensuing
    0.76
     بالای
    0.72
     workings
    0.71
     meisten
    0.71
     depred
    0.70
     někter
    0.70
     nuances
    0.70
    liğini
    0.69
    Activations Density 0.261%

    No Known Activations