© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    . or web links

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

    This neuron detects the boilerplate promotional phrasing used to introduce or advertise image/graphics galleries (e.g. “exclusively for you,” “among our finest photos gallery,” “images,” “graphics,” “for”).

    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
     படத்தில்
    0.62
     infile
    0.55
     largos
    0.54
     enclose
    0.53
     concat
    0.52
    ([],
    0.52
     maga
    0.52
     longitud
    0.51
    られました
    0.50
    贋
    0.50
    POSITIVE LOGITS
    Эти
    0.62
    ACI
    0.57
    दयाल
    0.54
    Estimated
    0.54
    Тех
    0.53
    Thinking
    0.52
    atici
    0.52
    Nonetheless
    0.52
     ANZ
    0.52
    Laurie
    0.52
    Activations Density 0.032%

    No Known Activations