© 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. 13499
    Prev
    Next
    INDEX
    Explanations

    random numbers or integers

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

    The neuron fires on semantically rich content words (nouns, verbs, adjectives, adverbs) rather than common function words.

    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
     DOWN
    0.86
    َ
    0.83
     APPLY
    0.77
     preceding
    0.75
    BOOKS
    0.74
    蜚
    0.73
     WINDOW
    0.72
     BOOKS
    0.71
     î
    0.71
     BATH
    0.71
    POSITIVE LOGITS
    isyon
    1.01
    тын
    0.86
     Fertilizer
    0.82
     değişik
    0.82
    ỏa
    0.79
     Eğitim
    0.79
    unun
    0.79
    टन
    0.79
     ആഘോഷ
    0.78
    ljen
    0.75
    Activations Density 0.000%

    No Known Activations