© 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. 2161
    Prev
    Next
    INDEX
    Explanations

    german common words

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

    This neuron activates on non-English (foreign language) 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_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
     вважа
    0.76
     estadounidense
    0.73
     yoki
    0.71
     Сасик
    0.70
    ༦
    0.69
     hoặc
    0.68
    ﭜ
    0.68
     khiến
    0.67
    द्वितीय
    0.66
    ະພັນ
    0.66
    POSITIVE LOGITS
     også
    1.27
     också
    1.16
     übrigens
    1.07
     also
    1.05
     alltid
    0.96
     derfor
    0.93
     totiž
    0.93
     å
    0.90
     både
    0.90
     nämlich
    0.90
    Activations Density 0.038%

    No Known Activations