© 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. 12287
    Prev
    Next
    INDEX
    Explanations

    vs. comparison

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

    This neuron fires on content-bearing words (key nouns, verbs, and adjectives) rather than on 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
    B
    0.88
    來講
    0.74
    W
    0.71
    J
    0.71
    V
    0.70
    I
    0.69
    T
    0.67
    package
    0.66
    R
    0.66
    E
    0.65
    POSITIVE LOGITS
    리
    0.91
    м
    0.88
    수한
    0.88
    가의
    0.86
    녀
    0.84
    리의
    0.84
    iyeti
    0.83
    리에
    0.82
    杝
    0.82
     direta
    0.81
    Activations Density 0.000%

    No Known Activations