© 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. 7883
    Prev
    Next
    INDEX
    Explanations

    factual questions about quantity, location, or definitions

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

    The neuron fires on promotional call-to-action clauses (e.g. “if you want to get… click/save…”) that invite the reader to download or obtain something.

    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
    쌔
    0.90
     maniac
    0.79
    ць
    0.77
    ব্যব
    0.76
     ecmaVersion
    0.76
     hernia
    0.76
    ına
    0.75
    cado
    0.75
    وندی
    0.75
     entró
    0.75
    POSITIVE LOGITS
     Persons
    0.76
     LT
    0.75
     Various
    0.75
     MN
    0.73
     Da
    0.73
     Kini
    0.72
     Non
    0.71
     Repeated
    0.71
     Л
    0.71
     хорошее
    0.71
    Activations Density 0.000%

    No Known Activations