© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5918
    Prev
    Next
    INDEX
    Explanations

    capture image or art

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

    The neuron fires on marketing‐style, promotional product descriptions—i.e. sales copy filled with praise, superlatives, and advertising 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
     […]
    0.71
     startups
    0.70
     superheroes
    0.70
     dashboards
    0.70
     chatbots
    0.68
     newbies
    0.68
     superman
    0.67
     stupid
    0.66
     hoodies
    0.66
    🤪
    0.65
    POSITIVE LOGITS
    历史
    0.86
     circa
    0.86
    Historical
    0.86
    circa
    0.84
    歷史
    0.82
     Historical
    0.80
    historical
    0.80
    Historic
    0.79
     चित्रण
    0.78
     ചിത്രം
    0.77
    Activations Density 0.037%

    No Known Activations