© 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. 16017
    Prev
    Next
    INDEX
    Explanations

    code and specific entities

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

    The neuron responds to unusually rare or content‐rich words (i.e. low‐frequency tokens).

    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
     жив
    0.85
    зад
    0.82
    तः
    0.79
     обратно
    0.75
    IAMS
    0.74
     partielle
    0.74
     rojos
    0.71
    용
    0.70
     хороший
    0.70
     ハン
    0.70
    POSITIVE LOGITS
     auditory
    0.77
    tof
    0.76
    ąż
    0.73
    perc
    0.73
     roadmap
    0.73
     cutaneous
    0.73
     worldview
    0.73
    龐
    0.72
    ır
    0.70
     শৈ
    0.70
    Activations Density 0.000%

    No Known Activations