© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10338
    Prev
    Next
    INDEX
    Explanations

    Polish and Czech/Slovak geography and queries

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

    The neuron fires on terms that introduce or enumerate product features or offerings in a marketing‐style list.

    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
    ୈ
    1.07
    ୌ
    0.98
    븐
    0.96
    lés
    0.91
    ଖ
    0.91
    룀
    0.91
     합니다
    0.85
     congregate
    0.84
    ларда
    0.84
    ୃ
    0.84
    POSITIVE LOGITS
     też
    1.90
     przy
    1.84
     był
    1.64
     jeszcze
    1.63
     bardzo
    1.60
     Ł
    1.57
     przed
    1.55
     oraz
    1.55
     sł
    1.55
     jednak
    1.55
    Activations Density 0.152%

    No Known Activations