© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41046
    Prev
    Next
    INDEX
    Explanations

    Roosevelt and FDR related contexts

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

    The neuron is highly activated by occurrences of the name “Roosevelt,” particularly references to Franklin Delano Roosevelt.

    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
     '
    -2.63
    ípio
    -2.14
    由於
    -2.11
    跄
    -2.11
     pude
    -2.08
    </b>
    -2.03
     accolades
    -2.03
    up
    -2.02
    WHAT
    -2.02
    ..."
    -2.00
    POSITIVE LOGITS
    .’”
    2.50
    .
    2.42
    ’.”
    2.30
    䜣
    2.28
    </h3>
    2.28
    {
    2.25
    )’
    2.19
     ])
    2.16
     same
    2.14
    ↵
    2.13
    Activations Density 0.003%

    No Known Activations