© 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. 1126
    Prev
    Next
    INDEX
    Explanations

    important considerations and security

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

    The neuron fires on standalone section headings, UI labels, and call-to-action words (e.g. “Recommended,” “Related,” “Upload,” “Added to cart,” “View cart”).

    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
    倘
    0.58
     –
    0.54
     squarely
    0.54
     introspection
    0.54
    果然
    0.52
    opens
    0.52
     decently
    0.52
    உலக
    0.51
    –
    0.51
     albeit
    0.50
    POSITIVE LOGITS
     recomendado
    0.66
     Recomend
    0.64
     wikipagina
    0.62
     Content
    0.61
     Links
    0.60
     ഉപകരണ
    0.59
     Recommend
    0.57
     recomand
    0.57
     aján
    0.57
     References
    0.56
    Activations Density 0.758%

    No Known Activations