© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on German-language text, especially common German words and function 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
    ською
    0.81
    视为
    0.80
    chae
    0.79
    Additionally
    0.77
    ському
    0.77
     імені
    0.77
    随后
    0.76
    畯
    0.75
    ⛎
    0.74
    列表中
    0.73
    POSITIVE LOGITS
     verschiedene
    1.39
     kleine
    1.38
     neue
    1.33
     nieuwe
    1.31
     große
    1.31
     großes
    1.28
     spezielle
    1.27
     viele
    1.26
     grote
    1.22
     weitere
    1.21
    Activations Density 0.078%

    No Known Activations