© 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. 12759
    Prev
    Next
    INDEX
    Explanations

    paths ending in app, catch, bin

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

    The neuron fires strongly on Devanagari-script tokens (i.e. Hindi words).

    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
    お願い
    0.62
    も見
    0.60
    utile
    0.59
    どの
    0.59
     mengambil
    0.57
    システムの
    0.57
     vilken
    0.57
    武
    0.56
    するとき
    0.56
     چاہتا
    0.56
    POSITIVE LOGITS
     का
    0.86
     ਦਾ
    0.79
     کا
    0.78
     से
    0.77
     की
    0.74
     में
    0.73
     ने
    0.71
     ਦੀ
    0.71
     को
    0.69
     पर
    0.67
    Activations Density 0.004%

    No Known Activations