© 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. 9404
    Prev
    Next
    INDEX
    Explanations

    leap year

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

    The neuron spotlights numeric tokens that include a decimal point—most often fragments of phone‐number–style sequences.

    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
    及び
    0.69
    جموع
    0.68
    ين
    0.66
     এছাড়া
    0.64
    0.64
     Medieval
    0.63
     À
    0.63
     medieval
    0.62
    これで
    0.62
    牘
    0.61
    POSITIVE LOGITS
    𝒽
    0.89
    Sprintf
    0.88
    ज़ाइन
    0.87
    szlig
    0.87
    THz
    0.86
    대
    0.84
     noh
    0.84
    al
    0.84
    MnO
    0.82
     YoY
    0.81
    Activations Density 0.002%

    No Known Activations