© 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. 58029
    Prev
    Next
    INDEX
    Explanations

    Mocking and Assertions

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

    The neuron fires on programming source‐code tokens (identifiers, keywords, and symbols) in technical Q&A excerpts.

    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
     poached
    -0.72
    笈
    -0.71
    GN
    -0.71
     番目
    -0.71
    laquo
    -0.71
    lichte
    -0.71
     控
    -0.69
     Houd
    -0.68
     choix
    -0.68
    gette
    -0.68
    POSITIVE LOGITS
     Moq
    0.87
     verify
    0.85
     Verify
    0.81
    Mock
    0.80
     mock
    0.79
    něž
    0.79
    mock
    0.78
    Verifier
    0.78
     Mock
    0.77
    ifer
    0.76
    Activations Density 0.002%

    No Known Activations