© 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. 10-GEMMASCOPE-RES-131K
    7. 90345
    Prev
    Next
    INDEX
    Explanations

    voters choosing candidates

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

    The neuron fires on numerical election statistics—counts or percentages of voters or electors (e.g. “voters 366,” “voters in 57,” “electors 53,” “in 53.5 Virginia”), i.e. numerical data about voting.

    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
     \_
    -3.27
    </em>
    -2.89
    }{
    -2.67
     flurry
    -2.45
    \_
    -2.45
    ]
    -2.38
    ,"
    -2.36
    ).
    -2.31
    ?"
    -2.28
    ’
    -2.28
    POSITIVE LOGITS
     extraordinaire
    2.88
    </i>
    2.80
    塤
    2.58
    籥
    2.47
    </h1>
    2.45
    踯
    2.36
    盦
    2.33
    鹮
    2.31
     They
    2.30
    ⃚
    2.27
    Activations Density 0.004%

    No Known Activations