© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8888
    Prev
    Next
    INDEX
    Explanations

    calendar and inbox management

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

    The main thing this neuron does is find numeric values (often with accompanying symbols like “%”) and other statistics or quantitative measurements 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_31_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
     <*>
    0.63
     \<
    0.58
    <^
    0.56
     Graduates
    0.55
     <
    0.54
     EditorGUILayout
    0.54
     Moderators
    0.54
     Announcements
    0.54
     急
    0.54
     محمد
    0.52
    POSITIVE LOGITS
    Nak
    0.66
    Pine
    0.62
    parts
    0.57
    outlook
    0.56
     feats
    0.54
     nỗi
    0.54
     sme
    0.53
     parts
    0.53
    Spart
    0.52
     outlook
    0.52
    Activations Density 0.052%

    No Known Activations