© 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. 66
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related words in multiple languages

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

    The neuron strongly activates on terms and phrases related to marketing and search‐engine‐optimization (SEO) jargon.

    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
    0
    0.63
    0.55
     Tuesday
    0.55
    4
    0.54
    uesday
    0.53
    2
    0.53
     Joe
    0.52
    5
    0.52
    3
    0.51
    C
    0.51
    POSITIVE LOGITS
     вследствие
    0.66
     மற்றும்
    0.58
     посредством
    0.58
     microorganisms
    0.56
     macromolecules
    0.56
     curvatures
    0.56
     physicochemical
    0.55
     microorganism
    0.54
     xhrObj
    0.54
     путем
    0.54
    Activations Density 10.123%

    No Known Activations