© 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. 11930
    Prev
    Next
    INDEX
    Explanations

    LangChain and language models

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

    The neuron strongly fires on occurrences of the proper noun “Langdon.”

    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
    cari
    0.55
    럇
    0.53
     batalha
    0.51
     pelea
    0.50
    ौनक
    0.50
    చ్చ
    0.50
     amigas
    0.50
     Chin
    0.49
    窅
    0.49
     habitantes
    0.49
    POSITIVE LOGITS
    ‫
    0.56
    ‏
    0.55
    らか
    0.55
    lect
    0.54
    pliance
    0.54
    mich
    0.54
     ▪
    0.52
    lois
    0.51
    ford
    0.50
    orous
    0.50
    Activations Density 0.064%

    No Known Activations