© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47827
    Prev
    Next
    INDEX
    Explanations

    special counsel and grand juries

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

    This neuron responds to named entities—especially people’s names and official titles.

    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
     Num
    -0.86
     wahl
    -0.79
    Textbook
    -0.73
     violento
    -0.70
    Xd
    -0.70
     winning
    -0.69
     Gyro
    -0.69
     Turquoise
    -0.69
     الأح
    -0.68
     Flaming
    -0.68
    POSITIVE LOGITS
     Starr
    1.46
     Monica
    1.29
    Monica
    1.18
     Lew
    1.15
     Nixon
    1.05
     Clinton
    1.01
    Lew
    0.97
     Kenneth
    0.96
     impeachment
    0.93
    Clinton
    0.91
    Activations Density 0.027%

    No Known Activations