© 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. 10985
    Prev
    Next
    INDEX
    Explanations

    `:latest` or `styles`

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

    The neuron fires strongly on low‐frequency or otherwise unusual subword tokens (i.e. rare, unexpected pieces of words).

    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
    )}_{\
    0.81
    ۹
    0.80
    かけ
    0.77
    なかった
    0.76
    かけた
    0.75
    _{\
    0.75
    みた
    0.75
    方的
    0.74
    _{
    0.73
    面的
    0.73
    POSITIVE LOGITS
     ▪
    0.86
     LES
    0.77
     MAINT
    0.76
     ✓
    0.75
    belle
    0.75
     Woodbridge
    0.75
     রাজ্যে
    0.74
     الذي
    0.73
    uellement
    0.72
     WOOD
    0.72
    Activations Density 0.000%

    No Known Activations