© 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. 8638
    Prev
    Next
    INDEX
    Explanations

    representing numerical indices

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

    The neuron fires on words commonly used in webpage or article metadata (e.g. “published,” “posted,” “accessed,” “last edited”).

    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
    iszt
    0.96
    jenje
    0.89
    ிருப்பது
    0.87
     Quels
    0.86
    uleux
    0.82
    েল
    0.80
    ყ
    0.79
    unately
    0.79
    jenja
    0.79
     immobilier
    0.79
    POSITIVE LOGITS
     responder
    0.94
     возраста
    0.79
     произо
    0.77
     пользователь
    0.77
     terá
    0.75
     содержа
    0.74
     emotion
    0.73
     bulb
    0.73
     braids
    0.73
     powerhouse
    0.73
    Activations Density 0.001%

    No Known Activations