© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5679
    Prev
    Next
    INDEX
    Explanations

    dialogue starts

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

    The neuron is a strong detector for numeric tokens (especially floating‐point or year-style numbers).

    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
    如果我们
    0.63
     Energía
    0.61
    讓
    0.61
    讓我們
    0.59
    让
    0.59
    能够
    0.58
    認為
    0.58
    我們
    0.57
     我们
    0.57
    让我们
    0.57
    POSITIVE LOGITS
     γε
    0.64
    !),
    0.62
    !;
    0.58
    !)
    0.56
    ர்ப
    0.55
    alu
    0.55
    .),
    0.55
    atore
    0.54
    栝
    0.54
     btw
    0.54
    Activations Density 0.006%

    No Known Activations