© 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. 4781
    Prev
    Next
    INDEX
    Explanations

    approval and time

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

    This neuron responds to salient content-bearing words—especially uncommon or emphatic nouns and adjectives—rather than to 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
    ك
    0.98
    硬
    0.93
    正则
    0.87
    س
    0.76
    थे
    0.73
     endif
    0.71
     échanc
    0.70
     sulfite
    0.69
    TextAppearance
    0.67
    填
    0.67
    POSITIVE LOGITS
    ub
    0.77
    wil
    0.72
    ada
    0.71
    াত
    0.71
     tudo
    0.71
     wil
    0.71
     Bhi
    0.71
    mselves
    0.71
     Party
    0.70
    od
    0.70
    Activations Density 0.001%

    No Known Activations