© 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. 9985
    Prev
    Next
    INDEX
    Explanations

    calculate radius, distance from center

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

    The neuron strongly activates on linking or connective function words—particularly relative‐clause markers like “other” and “which”—that introduce subordinate clauses.

    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
    呐
    0.74
    −
    0.73
    cena
    0.72
    うち
    0.70
    v
    0.69
     प्रार्थना
    0.68
    視野
    0.68
    祈
    0.68
     Spears
    0.68
     discoloration
    0.66
    POSITIVE LOGITS
    پلز
    0.94
     esegu
    0.93
     dettag
    0.91
     articolo
    0.88
     dettaglio
    0.86
    retail
    0.84
    दिग्ध
    0.82
    ㅇ
    0.82
     Italiana
    0.80
     sehari
    0.80
    Activations Density 0.000%

    No Known Activations