© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11955
    Prev
    Next
    INDEX
    Explanations

    selling proposition

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

    The neuron detects words characteristic of legal or policy disclaimer sections (e.g. liability, terms, privacy, damages).

    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_24_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
     ||
    0.75
     ==
    0.73
     =
    0.72
    id
    0.72
    %;
    0.72
     ===========
    0.71
    卞
    0.70
     -
    0.69
     //
    0.67
     +
    0.67
    POSITIVE LOGITS
     manchas
    0.90
     něk
    0.88
    клады
    0.86
    мы
    0.85
    भरा
    0.84
    рын
    0.84
     conversar
    0.84
     worldview
    0.84
     গবেষণ
    0.83
    designs
    0.82
    Activations Density 0.000%

    No Known Activations