© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13351
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of “24 hours” (often in the context of “24/7” around-the-clock availability).

    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
     \
    0.64
    er
    0.63
    ?
    0.63
     /
    0.62
     subscribing
    0.62
    +...+
    0.59
    _
    0.59
    ar
    0.59
    อาจ
    0.59
    搜索
    0.58
    POSITIVE LOGITS
     vibhav
    0.82
     fases
    0.77
    érêt
    0.76
    فاظ
    0.76
     funções
    0.75
     fiestas
    0.74
    रिमेंट
    0.73
     تعاون
    0.72
    imizin
    0.71
    aisesti
    0.71
    Activations Density 0.001%

    No Known Activations