© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    Okay, let's

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

    The neuron strongly fires on passages containing hard data—numbers, dates, statistics—and source‐attribution phrases (e.g. “according to X,” percentages, measurements).

    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
    iß
    0.54
     '.</
    0.52
     নামে
    0.51
     ทั้ง
    0.50
     ন্যায়
    0.50
     lớn
    0.50
     বাহিনীকে
    0.50
     ফোর্স
    0.50
    🫰
    0.50
     большую
    0.49
    POSITIVE LOGITS
     Jennifer
    1.59
     sociologist
    1.53
     anthropologist
    1.51
     Professor
    1.50
     Andrew
    1.50
     economist
    1.48
     Stephanie
    1.46
     Michael
    1.44
    Jennifer
    1.44
     Eric
    1.42
    Activations Density 0.719%

    No Known Activations