© 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. 112815
    Prev
    Next
    INDEX
    Explanations

    Downing Street politicians

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

    The neuron strongly activates on proper names and terms tied to British politics, such as politicians’ names, party names, and key political institutions.

    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
    They
    -1.45
    !"
    -1.41
     will
    -1.40
    л
    -1.34
     они
    -1.33
     их
    -1.31
    --"
    -1.31
     respectivamente
    -1.30
    ?"
    -1.30
    ,"
    -1.30
    POSITIVE LOGITS
     couvert
    1.22
     assures
    1.22
     pursues
    1.20
     impec
    1.19
    内に
    1.16
    sillo
    1.14
     другим
    1.14
     Befehl
    1.13
     интерьера
    1.13
    ⏑
    1.12
    Activations Density 0.010%

    No Known Activations