© 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. 92921
    Prev
    Next
    INDEX
    Explanations

    the results of studies

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

    The neuron is primarily triggered by occurrences of the definite article “the.”

    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
    *</
    -1.63
    voer
    -1.55
    …»
    -1.40
    !»
    -1.38
    🖐
    -1.37
    »;
    -1.36
    💞
    -1.35
    📱
    -1.34
    💫
    -1.34
    ...»
    -1.33
    POSITIVE LOGITS
     results
    3.02
     observed
    2.41
     findings
    2.28
     same
    2.27
     overall
    2.22
     lack
    2.19
     fact
    2.14
     reason
    2.13
     difference
    2.03
     use
    1.98
    Activations Density 0.152%

    No Known Activations