© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    alternative choices or comparisons

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

    This neuron activates on prominent content words—especially domain-specific or technical nouns and key terms.

    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
    /
    0.97
    various
    0.91
    например
    0.82
    യും
    0.82
    ແລະ
    0.80
    および
    0.79
    -/
    0.78
    และ
    0.75
     및
    0.75
    either
    0.75
    POSITIVE LOGITS
     oppure
    1.29
     OR
    0.97
     nor
    0.86
    还是
    0.82
    嗎
    0.82
    還是
    0.79
    吗
    0.75
    )||
    0.73
     নাকি
    0.71
    なのか
    0.71
    Activations Density 0.138%

    No Known Activations