© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5491
    Prev
    Next
    INDEX
    Explanations

    time and numbers with punctuation

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

    The neuron is detecting numeric timestamps (date‐time values composed of digits and colons).

    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
    lytres
    0.63
     कॉले
    0.59
    authority
    0.57
     स्वर्
    0.57
    午
    0.56
    美国的
    0.55
     नॉलेज
    0.55
     বাসস্থান
    0.55
    於
    0.55
     নৈ
    0.54
    POSITIVE LOGITS
     tout
    0.58
     vol
    0.55
     verde
    0.55
     MST
    0.55
    GUILayout
    0.52
     daging
    0.52
     bietet
    0.51
     CST
    0.49
     EST
    0.48
     bieden
    0.48
    Activations Density 0.036%

    No Known Activations