© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2762
    Prev
    Next
    INDEX
    Explanations

    etcetera and lists

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

    The neuron activates on multi‐word technical or industrial noun phrases (compound terms describing specialized products, materials, or services).

    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
    :
    0.86
    َ
    0.71
    ?
    0.70
    =
    0.67
    ();
    0.66
    ン
    0.62
    TE
    0.61
     này
    0.61
    ():
    0.59
     这个
    0.59
    POSITIVE LOGITS
     etc
    1.08
    etc
    0.92
     ইত্যাদি
    0.84
     وغیرہ
    0.82
    などで
    0.79
     इत्यादी
    0.79
    などに
    0.78
    などは
    0.78
    等方面
    0.77
     тощо
    0.76
    Activations Density 0.167%

    No Known Activations