© 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. 12216
    Prev
    Next
    INDEX
    Explanations

    characters and code structure

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

    The neuron strongly activates on occurrences of the token “Gene” in dataset or study‐title contexts.

    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
    ্বরূপ
    0.78
     wattage
    0.78
     dizzy
    0.78
    チック
    0.73
     circumfer
    0.72
    費
    0.71
    титься
    0.71
     antire
    0.70
    ورك
    0.69
    cribed
    0.68
    POSITIVE LOGITS
    che
    0.91
    ים
    0.89
    L
    0.88
    タ
    0.88
     テ
    0.86
     altri
    0.83
    K
    0.83
    ség
    0.82
    W
    0.81
    h
    0.80
    Activations Density 0.000%

    No Known Activations