© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91496
    Prev
    Next
    INDEX
    Explanations

    dq transformation

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

    The neuron detects technical or engineering–style terminology—especially domain-specific jargon and acronyms common in electrical‐engineering texts.

    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
     modelAndView
    -0.77
    rout
    -0.73
     жиз
    -0.72
    からない
    -0.71
     balm
    -0.70
    Rudi
    -0.68
     studen
    -0.68
    jzen
    -0.68
     Rudi
    -0.67
    Svc
    -0.67
    POSITIVE LOGITS
     Park
    0.99
    Park
    0.95
    mijn
    0.85
     Concordia
    0.82
    abc
    0.81
     PARK
    0.81
    park
    0.79
     park
    0.79
     dq
    0.77
     axis
    0.77
    Activations Density 0.029%

    No Known Activations