© 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. 14906
    Prev
    Next
    INDEX
    Explanations

    specific financial and health quantities

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

    The neuron strongly activates on very high‐frequency/common tokens (e.g. “feel,” “free,” “to,” “payment,” “accept,” etc.), i.e. it flags the most frequent, “stopword”-like or everyday words.

    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
     proprietà
    0.77
     Software
    0.75
    ما
    0.73
    軒
    0.72
    mm
    0.71
    可靠
    0.71
    à
    0.71
    ű
    0.71
    ha
    0.69
    र्थ
    0.67
    POSITIVE LOGITS
     divulge
    0.83
     впоследствии
    0.81
     Перейти
    0.80
     overthrow
    0.80
     Actualmente
    0.79
     indicó
    0.77
     нач
    0.76
     Conoc
    0.76
     disrupt
    0.76
     Evel
    0.76
    Activations Density 0.000%

    No Known Activations