© 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. 10-GEMMASCOPE-RES-131K
    7. 71808
    Prev
    Next
    INDEX
    Explanations

    names preceded by Dr

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

    The neuron specifically detects the period in the honorific “Dr.”, i.e. occurrences of the “Dr.” abbreviation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ⸂
    -2.73
    ឵
    -2.55
    </strong>
    -2.50
    </em>
    -2.42
    
    -2.38
    ☫
    -2.34
    埛
    -2.31
    ouncements
    -2.28
     deceptive
    -2.28
    
    -2.25
    POSITIVE LOGITS
     even
    2.42
     it
    2.30
    N
    2.23
    鱟
    2.19
     that
    2.11
     {
    2.05
    ’,
    2.03
     there
    2.03
    ための
    2.02
    ES
    2.00
    Activations Density 0.005%

    No Known Activations