© 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. 31-GEMMASCOPE-2-RES-16K
    7. 157
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to marketing-style text—particularly brand or service names and promotional language.

    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
     (
    0.39
    0.34
     wich
    0.32
     จึง
    0.30
     M
    0.30
    /
    0.30
     B
    0.30
    B
    0.30
    K
    0.29
    ´
    0.29
    POSITIVE LOGITS
    ⅽ
    0.41
    ⅾ
    0.36
    ᧐
    0.35
     belongings
    0.33
     benutzer
    0.33
    ⲟ
    0.33
    льнявыя
    0.33
     एक्चुअली
    0.33
     fico
    0.33
    Ⲟ
    0.33
    Activations Density 2.282%

    No Known Activations