© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6171
    Prev
    Next
    INDEX
    Explanations

    adult sexual roleplay

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

    The neuron strongly activates on numeric tokens containing decimal points (e.g. journal volume, issue, DOI, or page numbers).

    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
     девя
    0.96
     Borges
    0.90
     Tolstoy
    0.88
    )));
    0.86
     Rowling
    0.86
     adecu
    0.86
     rRNA
    0.84
     Padukone
    0.84
     связаны
    0.83
     двадцать
    0.83
    POSITIVE LOGITS
    ח
    0.97
    ні
    0.79
    انى
    0.79
    نج
    0.75
    ן
    0.74
    ون
    0.73
    ەس
    0.72
     BRA
    0.71
    פע
    0.71
    ס
    0.70
    Activations Density 0.001%

    No Known Activations