© 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. 7436
    Prev
    Next
    INDEX
    Explanations

    disclaimers at the end

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

    This neuron detects boilerplate attribution lines of the form “The post … appeared first on …,” i.e. publisher/source credit statements.

    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
     Resume
    0.48
     термин
    0.48
    otide
    0.47
    ilene
    0.46
     sukh
    0.46
    씌
    0.46
    itioner
    0.45
     प्राइम
    0.45
     ตุลาคม
    0.45
    ография
    0.45
    POSITIVE LOGITS
     répar
    0.43
     înd
    0.42
     الأصل
    0.42
    অতি
    0.42
    值的
    0.41
    selectedValue
    0.40
    佳
    0.40
     особливо
    0.40
     cott
    0.39
    点的
    0.39
    Activations Density 0.059%

    No Known Activations