© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    function call or code keywords

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

    The neuron primarily activates on numeric tokens—especially decimal and large numbers—highlighting sequences of digits in the text.

    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
    ज
    0.82
    িয়াছেন
    0.79
     bamb
    0.77
    كتب
    0.75
     enl
    0.75
     आहे
    0.73
    MAG
    0.73
    ञ
    0.72
     encycl
    0.71
     aprob
    0.70
    POSITIVE LOGITS
    чены
    0.86
    coords
    0.82
    られる
    0.81
    0.79
    UserManager
    0.77
    nonzero
    0.76
    𝑡
    0.76
    tenance
    0.75
    BeanFactory
    0.75
    TouchableOpacity
    0.75
    Activations Density 0.001%

    No Known Activations