© 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. 14558
    Prev
    Next
    INDEX
    Explanations

    why I will

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

    The neuron is a detector for relatively “content‐heavy” words—i.e. uncommon multisyllabic nouns, verbs, adjectives, and adverbs—rather than function or stop 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
     мы
    0.87
    鹖
    0.87
    Те
    0.83
     seja
    0.82
    ווע
    0.82
    ἢ
    0.81
    эта
    0.80
     ukup
    0.80
     thế
    0.79
     questões
    0.79
    POSITIVE LOGITS
    ameni
    0.79
     “
    0.73
     Lawyers
    0.71
     diment
    0.71
    からない
    0.70
    (&
    0.70
    ('@
    0.69
    auen
    0.67
    ('/
    0.66
    じて
    0.65
    Activations Density 0.000%

    No Known Activations