© 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. 13371
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of the word “students.”

    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
    president
    0.88
    fem
    0.86
    graf
    0.82
    м
    0.81
     ebenfalls
    0.79
    ные
    0.79
    diet
    0.78
     wynosi
    0.74
    te
    0.73
    نا
    0.72
    POSITIVE LOGITS
    𝙃
    0.80
    𝐎
    0.74
     Giải
    0.71
    ⚓
    0.71
    💪
    0.70
     انگیز
    0.69
    𝒞
    0.68
    𝙍
    0.68
    ことができる
    0.67
    ágoras
    0.67
    Activations Density 0.000%

    No Known Activations