© 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. 9997
    Prev
    Next
    INDEX
    Explanations

    Hugging Face

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

    The neuron fires on occurrences of “High” in the names of high schools, i.e. when the text mentions a high school.

    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
    stvu
    0.89
    stva
    0.77
     بتاع
    0.75
    ishly
    0.75
    нду
    0.75
    ‑
    0.74
    liness
    0.74
    ЕЛ
    0.73
    atka
    0.73
    owler
    0.73
    POSITIVE LOGITS
     କରି
    0.67
     l
    0.65
     sıral
    0.62
     can
    0.61
     komplik
    0.61
    运输
    0.59
     Interval
    0.58
    0.58
     Cou
    0.57
     Kollegen
    0.56
    Activations Density 0.004%

    No Known Activations