© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    find: to, if, calculate

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

    The neuron is looking for numeric values—especially measurements, statistics, and decimal numbers—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
    লাইট
    0.82
    Choisissez
    0.78
    
    0.76
     использу
    0.74
     использовать
    0.70
    َ
    0.70
     ज़कात
    0.69
    ͈
    0.69
     Jugendliche
    0.68
     ভাইয়ের
    0.68
    POSITIVE LOGITS
     afresh
    0.99
     upto
    0.94
     suo
    0.91
     bhi
    0.89
     Nagpur
    0.89
     envis
    0.88
     expiry
    0.88
     opined
    0.88
     aforesaid
    0.87
     envisaged
    0.87
    Activations Density 0.028%

    No Known Activations