© 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. 8456
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

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

    The neuron is tuned to detect numeric tokens and numeric expressions (digits, decimal numbers, percentages).

    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
     און
    0.54
    ストア
    0.50
    QUIN
    0.50
    ዚ
    0.50
    VE
    0.50
    Collegamenti
    0.49
    ImageView
    0.49
    נדה
    0.49
    <0xAD>
    0.49
    覇
    0.49
    POSITIVE LOGITS
     나머지
    0.99
     remaining
    0.96
     remainder
    0.87
     Remaining
    0.83
     나머
    0.82
     restante
    0.81
    remainder
    0.80
    remaining
    0.79
     restantes
    0.79
     two
    0.78
    Activations Density 0.177%

    No Known Activations