© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2269
    Prev
    Next
    INDEX
    Explanations

    comprehensive explanation

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

    This neuron detects occurrences of the verb “cover” (and its inflected forms).

    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
    ப்
    0.83
     một
    0.79
     déterminer
    0.75
     sebuah
    0.74
     një
    0.73
     cái
    0.72
    一种
    0.72
    脯
    0.72
     unei
    0.71
    một
    0.71
    POSITIVE LOGITS
    ทั้งหมด
    1.15
    すべての
    1.08
     всех
    1.05
     semua
    1.02
     everything
    0.95
    あらゆる
    0.93
    すべて
    0.93
     all
    0.91
     wszystkich
    0.91
     всіх
    0.91
    Activations Density 0.065%

    No Known Activations