© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3654
    Prev
    Next
    INDEX
    Explanations

    phrases following "with"

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

    The neuron primarily activates on decimal numeric tokens (floating‐point numbers) in product or item specifications.

    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
    roep
    0.62
    ಧಾರವಾಡ
    0.59
    ባቢ
    0.57
    kadang
    0.57
    =\
    0.55
    seu
    0.54
    اتھ
    0.53
    ikir
    0.53
    ophysics
    0.52
    washington
    0.52
    POSITIVE LOGITS
    ل
    0.68
     Q
    0.57
     C
    0.57
     R
    0.55
    Q
    0.55
     K
    0.54
     ź
    0.54
     T
    0.52
     использованием
    0.52
     M
    0.51
    Activations Density 0.032%

    No Known Activations