© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2047
    Prev
    Next
    INDEX
    Explanations

    to the

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

    The neuron is specialized in spotting numeric tokens—especially floating-point numbers or measurements—in the text.

    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
    k
    1.06
    s
    1.03
    l
    1.00
    p
    0.92
    e
    0.91
    c
    0.91
    b
    0.90
    es
    0.88
    f
    0.86
    ar
    0.85
    POSITIVE LOGITS
     accommodate
    1.15
     appease
    1.14
     ensure
    1.08
     mitigate
    1.08
     alleviate
    1.08
    ppled
    1.08
     counteract
    1.07
     lessen
    1.01
     enhance
    0.99
     maximize
    0.97
    Activations Density 0.724%

    No Known Activations