© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    explain why

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

    The neuron strongly activates on occurrences of the verb “explain” (and its morphological variants such as “explanation”).

    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
    </b>
    -1.34
     información
    -0.95
    </sup>
    -0.95
    aziland
    -0.94
    uellement
    -0.94
     information
    -0.93
    /
    -0.92
    ')
    -0.90
     сможете
    -0.90
     الأشخاص
    -0.90
    POSITIVE LOGITS
     why
    2.97
     how
    2.19
    why
    1.63
     away
    1.60
     dlaczego
    1.48
    为什么
    1.46
     kenapa
    1.44
    どうして
    1.42
     WHY
    1.37
     to
    1.36
    Activations Density 0.025%

    No Known Activations