© 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. 92867
    Prev
    Next
    INDEX
    Explanations

    mechanisms and causes

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

    The neuron detects mentions of “missing” (especially in the phrase “missing data” or “missing mechanism”) and related qualifiers like “ignorable.”

    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
     Mulberry
    -0.94
     MARTIN
    -0.88
     Mapper
    -0.86
     millet
    -0.84
    Mapper
    -0.84
    MARTIN
    -0.82
    Marty
    -0.81
    weilen
    -0.80
     Magician
    -0.80
     局
    -0.78
    POSITIVE LOGITS
     mechanism
    6.56
     mechanisms
    5.97
     Mechanism
    4.94
     Mechanisms
    4.81
    mechanism
    4.78
    Mechanism
    4.56
     механи
    4.50
     mecanismo
    4.44
    Mechanisms
    4.09
    mechan
    4.00
    Activations Density 0.285%

    No Known Activations