© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77943
    Prev
    Next
    INDEX
    Explanations

    exam and certification materials

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

    The neuron activates strongly on sequences of digits (often with hyphens) that denote technical identifiers or exam codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturen
    -0.77
    obrá
    -0.76
    guém
    -0.74
    cuerdo
    -0.73
    cessed
    -0.73
    tissu
    -0.72
    bague
    -0.71
    падает
    -0.71
    isesi
    -0.71
    唁
    -0.71
    POSITIVE LOGITS
     exam
    2.00
    exam
    1.66
     dumps
    1.59
     Exam
    1.55
     certification
    1.54
     exams
    1.50
     Certification
    1.39
    dumps
    1.38
    Exam
    1.31
     certifications
    1.26
    Activations Density 0.039%

    No Known Activations