© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1971
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of downloadable previous‐year exam question papers (often in PDF form) used for academic test preparation.

    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
    നില
    0.60
     Reasons
    0.59
     Nong
    0.57
     Memories
    0.55
     Sana
    0.55
    溥
    0.54
     Meetings
    0.54
    িল্প
    0.54
     Hes
    0.54
     Hope
    0.53
    POSITIVE LOGITS
     questions
    1.98
    题目
    1.97
    questions
    1.92
     question
    1.87
    題目
    1.83
    题
    1.83
    Questions
    1.79
     Questions
    1.76
    Question
    1.74
     प्रश्न
    1.73
    Activations Density 0.494%

    No Known Activations