© 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. 2671
    Prev
    Next
    INDEX
    Explanations

    origins and etymology

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

    This neuron detects dictionary‐style definition and etymology cues—words and phrases that introduce or quote a term’s “meaning,” origin, or translation.

    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
    plat
    0.62
    belief
    0.61
    simile
    0.60
    湪
    0.60
     由
    0.59
    ѝ
    0.59
    姏
    0.59
    ience
    0.58
    嚧
    0.58
    itoti
    0.58
    POSITIVE LOGITS
     big
    0.59
     re
    0.58
     AML
    0.55
     Re
    0.54
     No
    0.54
     little
    0.54
     Bio
    0.54
     Mega
    0.53
     Kati
    0.53
     DD
    0.52
    Activations Density 0.014%

    No Known Activations