© 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. 14948
    Prev
    Next
    INDEX
    Explanations

    quality sleep, quantum conditional, recent slang

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

    The neuron fires on numeral tokens (numbers and numeric expressions).

    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
    ība
    0.61
    ን
    0.61
    琀
    0.60
    ţia
    0.58
     reactant
    0.56
    ția
    0.55
    nosť
    0.55
    
    0.55
    ți
    0.55
    ﹐
    0.54
    POSITIVE LOGITS
     (!)
    1.00
    (!)
    0.95
     porque
    0.77
     потря
    0.67
     কেননা
    0.64
    porque
    0.64
     eftersom
    0.63
     (!
    0.62
    because
    0.62
    संस्करण
    0.61
    Activations Density 0.793%

    No Known Activations