© 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. 8463
    Prev
    Next
    INDEX
    Explanations

    The neuron flags standalone numeric tokens (e.g. price amounts or measurements).

    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
    یده
    0.86
    屽
    0.83
    ों
    0.73
    ພວກເຮົາ
    0.71
    وقع
    0.70
     call
    0.70
     embargo
    0.69
    ای
    0.68
     plight
    0.68
     Dispose
    0.68
    POSITIVE LOGITS
    ak
    1.12
    ad
    0.95
    ßen
    0.81
     Беларусь
    0.79
    foods
    0.79
    concerned
    0.79
    )}$-
    0.78
    akn
    0.78
    zo
    0.77
     röm
    0.77
    Activations Density 0.000%

    No Known Activations