© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70193
    Prev
    Next
    INDEX
    Explanations

    political party names

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

    The neuron strongly responds to mentions of political party names or their uppercase acronyms.

    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
    født
    -1.02
     ελλην
    -0.93
    匍
    -0.92
     gmina
    -0.90
    🦪
    -0.90
     dirinya
    -0.89
    ◆◇
    -0.89
     být
    -0.89
    Schriften
    -0.86
     geboren
    -0.85
    POSITIVE LOGITS
     leader
    1.74
     leaders
    1.48
     leadership
    1.35
     members
    1.20
     member
    1.18
     Party
    1.15
     party
    1.14
    leader
    1.05
     candidate
    1.04
    leaders
    0.98
    Activations Density 0.036%

    No Known Activations