© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5175
    Prev
    Next
    INDEX
    Explanations

    not mentioned

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

    The neuron strongly activates on parts of web addresses (e.g. “http://”, domain fragments, URLs).

    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
    ت
    0.88
    ميل
    0.79
    ين
    0.79
    n
    0.78
     Mun
    0.77
    先端
    0.77
    حاب
    0.76
     vlog
    0.76
    Zee
    0.76
     vapors
    0.76
    POSITIVE LOGITS
     Acuerdo
    0.79
     П
    0.75
     acuerdo
    0.73
     notizia
    0.72
     Hình
    0.71
     conformément
    0.70
    ải
    0.69
     ช
    0.66
    ારી
    0.66
    Οι
    0.66
    Activations Density 0.001%

    No Known Activations