© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    technical architecture components

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

    The neuron fires on open-class, content-bearing words (the substantive nouns, verbs, and adjectives) rather than on 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
     januar
    0.85
     februar
    0.84
     veranda
    0.83
     bungalow
    0.81
     Motel
    0.80
     anniversary
    0.80
     January
    0.79
     yearling
    0.79
     янва
    0.78
     Wife
    0.78
    POSITIVE LOGITS
     computationally
    0.85
     moléculas
    0.79
     macromolecules
    0.78
    GPUs
    0.78
     методы
    0.77
    を用いる
    0.77
     বিজ্ঞানীরা
    0.76
    👾
    0.76
     любых
    0.75
    を用いた
    0.74
    Activations Density 0.101%

    No Known Activations