© 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. 15445
    Prev
    Next
    INDEX
    Explanations

    specific situation

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

    The neuron fires on uncommon, information‐bearing “content” words (i.e. relatively rare vocabulary) 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
    слу
    0.84
    и
    0.81
    Մ
    0.80
     senza
    0.78
    În
    0.74
    І
    0.73
     leído
    0.73
    ਮ
    0.73
    不是
    0.71
     ż
    0.71
    POSITIVE LOGITS
     Серге
    0.72
     эффективность
    0.71
     headerShown
    0.71
     ενώ
    0.71
    koh
    0.70
     પ્રસ
    0.70
     млад
    0.70
     характери
    0.69
    kob
    0.69
     эффектив
    0.69
    Activations Density 0.000%

    No Known Activations