© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8530
    Prev
    Next
    INDEX
    Explanations

    section break or list item separator

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

    The neuron 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_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
    ...
    0.81
    :
    0.74
    Whatever
    0.70
    ir
    0.69
    OTH
    0.68
    irt
    0.66
    "
    0.66
    「
    0.66
    oth
    0.65
    &
    0.65
    POSITIVE LOGITS
     valamint
    1.84
     καθώς
    1.73
     which
    1.70
     그리고
    1.70
     illetve
    1.68
     तसेच
    1.63
     nonché
    1.63
     pero
    1.59
     tetapi
    1.57
     wobei
    1.55
    Activations Density 0.551%

    No Known Activations