© 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. 8218
    Prev
    Next
    INDEX
    Explanations

    auxiliary languages

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

    The neuron is tuned to detect parts of web addresses (URL tokens such as “http://” or “://”).

    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
     Audiobook
    0.90
    جاج
    0.78
    ৃঙ্খলা
    0.76
    まとめ
    0.75
    玩笑
    0.74
    ﺠ
    0.74
    issy
    0.73
    dades
    0.73
    ща
    0.72
     publique
    0.72
    POSITIVE LOGITS
    ก
    0.80
     olnud
    0.75
     quaisquer
    0.72
    름
    0.71
    후
    0.70
    Apellido
    0.69
     где
    0.68
    Inset
    0.67
    ⊠
    0.66
     ANY
    0.66
    Activations Density 0.000%

    No Known Activations