© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    making proactive mitigation

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

    The main thing this neuron does is detect numeric expressions (digits, dates, measurements, etc.) 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
    ﺹ
    0.93
     exclusivos
    0.91
     coffers
    0.88
     equilibrated
    0.84
     booklets
    0.82
    噱
    0.82
    ామని
    0.79
     outputs
    0.78
     Winfrey
    0.78
     orchards
    0.77
    POSITIVE LOGITS
    ou
    0.71
    un
    0.70
    time
    0.68
    ù
    0.68
     Texas
    0.66
    loop
    0.66
    ricia
    0.65
    :
    0.65
    ore
    0.65
    ā
    0.65
    Activations Density 0.001%

    No Known Activations