© 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. 784
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to identify numeric‐looking tokens—especially monetary figures and other multi‐digit numerical/statistical values.

    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
    ？
    0.71
    :
    0.69
    ?
    0.69
    but
    0.61
    But
    0.60
    (),
    0.58
    ؟
    0.57
    或者
    0.57
    だけど
    0.56
    っぽい
    0.54
    POSITIVE LOGITS
     Thank
    0.85
     Kudos
    0.76
     THANK
    0.75
     Gracias
    0.73
     Estamos
    0.72
     उत्कृष्ट
    0.72
     Undoubtedly
    0.68
     सराह
    0.68
     Kindly
    0.68
     thankful
    0.67
    Activations Density 0.000%

    No Known Activations