© 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. 101
    Prev
    Next
    INDEX
    Explanations

    math/code/summary/utility functions

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

    The neuron fires on words naming commercial services or rentable products (e.g. dumpster rental, cloud storage, pest control, medical detox, essay writing).

    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
    șit
    0.31
    archiviato
    0.27
    atlan
    0.26
     edn
    0.26
    ור
    0.25
    \<
    0.25
    тэ
    0.25
    >,
    0.25
    ography
    0.24
     пр
    0.24
    POSITIVE LOGITS
     Also
    0.39
     Juga
    0.37
     अद्भुत
    0.36
     देखील
    0.36
     ReturnVal
    0.36
     Ubuy
    0.36
    жуть
    0.34
     totalPrice
    0.34
     Moringa
    0.34
    的所有
    0.34
    Activations Density 0.057%

    No Known Activations