© 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. 6860
    Prev
    Next
    INDEX
    Explanations

    free, paid, version

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

    The neuron fires on promotional “try it free for X days” style offers—that is, free‐trial call-to-action 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
     Broncos
    0.62
     Bobcats
    0.61
     Wolverines
    0.60
     Sharks
    0.60
     Bunn
    0.59
     Panthers
    0.59
    돕
    0.58
     Rooster
    0.57
     Porter
    0.57
     Ozzy
    0.57
    POSITIVE LOGITS
    pregnant
    0.62
    ﾆ
    0.61
    ni
    0.57
    biological
    0.56
    办公
    0.54
     શાળા
    0.54
    จังหวัด
    0.54
    itling
    0.54
    ylim
    0.53
    Subtitle
    0.53
    Activations Density 0.000%

    No Known Activations