© 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. 7465
    Prev
    Next
    INDEX
    Explanations

    URL endpoints

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

    The neuron is primarily triggered by numeric tokens (e.g. ISBNs, DOIs, page numbers, and other decimal or integer strings).

    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
    Ghost
    0.64
    ">=
    0.62
     ريال
    0.61
     গুরুত্বপূর্ণ
    0.60
    जिए
    0.59
    Lite
    0.59
     ngram
    0.58
    }_{-
    0.57
     زیادی
    0.57
     પાર્
    0.56
    POSITIVE LOGITS
    它可以
    0.56
    inness
    0.55
    jedno
    0.54
    mäß
    0.53
     tepl
    0.52
     beneath
    0.52
    㳒
    0.51
    生物
    0.51
    ยาก
    0.50
     расте
    0.50
    Activations Density 0.016%

    No Known Activations