© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    common word prefixes in different languages

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

    This neuron detects non-English, foreign-language function words and prepositions (especially Slavic and Celtic tokens).

    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
    m
    0.73
    ir
    0.62
    nın
    0.62
    a
    0.61
    muy
    0.60
    iton
    0.59
    ี
    0.59
    u
    0.59
    et
    0.58
    na
    0.55
    POSITIVE LOGITS
     selben
    0.60
    вести
    0.59
    這個
    0.54
     berbagai
    0.54
     про
    0.54
     рамках
    0.53
     allerlei
    0.53
     formie
    0.53
     diesen
    0.52
     прид
    0.52
    Activations Density 0.012%

    No Known Activations