© 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. 13498
    Prev
    Next
    INDEX
    Explanations

    related to describing content

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

    The neuron strongly activates on numeric tokens containing a decimal point (i.e. floating-point 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
    s
    0.88
     rach
    0.84
     \
    0.78
    適
    0.73
     estamp
    0.73
     Thromb
    0.73
    sle
    0.70
    most
    0.70
     fizik
    0.69
    <\
    0.69
    POSITIVE LOGITS
    ർ
    0.75
    ication
    0.71
    एफआई
    0.71
     중심으로
    0.71
    једина
    0.70
    ംഗ്
    0.70
    ര്‍
    0.68
     articolo
    0.67
    棻
    0.66
    cluded
    0.66
    Activations Density 0.000%

    No Known Activations