© 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. 7237
    Prev
    Next
    INDEX
    Explanations

    violate guidelines or rules

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

    The neuron is specialized in spotting occurrences of the verb “follow” (and its inflected forms like “following” or “follow up”) in instructional contexts.

    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
    人心
    0.94
    isasi
    0.92
    pool
    0.91
     trao
    0.89
    ষ্ক
    0.88
    addSprite
    0.88
    дон
    0.88
    '">
    0.87
    лна
    0.87
     الخاصة
    0.85
    POSITIVE LOGITS
     stringent
    1.09
     normas
    1.09
     dictates
    1.07
     norme
    1.07
    h
    1.05
     требований
    1.05
     rules
    1.03
     strict
    1.01
     obligations
    1.00
     precepts
    1.00
    Activations Density 0.418%

    No Known Activations