© 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. 12508
    Prev
    Next
    INDEX
    Explanations

    difference between X and Y

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

    The neuron activates on words that signal comparisons or relationships—terms like “difference,” “race,” “battle,” “relationship,” and similar.

    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
     इति
    0.49
    anger
    0.48
    につなが
    0.47
     Drapeau
    0.46
    ኣ
    0.46
    arke
    0.46
    ത്തോ
    0.45
    ዝ
    0.45
    utt
    0.44
    akuwa
    0.44
    POSITIVE LOGITS
     between
    5.16
     между
    4.88
    between
    4.78
     zwischen
    4.53
     між
    4.50
     Between
    4.44
     mellom
    4.44
    Between
    4.41
     mellan
    4.41
     tussen
    4.38
    Activations Density 0.734%

    No Known Activations