© 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. 101091
    Prev
    Next
    INDEX
    Explanations

    Sarah Palin and other public figures

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

    This neuron detects capitalized political proper names and policy terms (e.g. politician names and named political initiatives).

    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
    ycznej
    -1.57
    zegovina
    -1.51
     While
    -1.40
    Secara
    -1.40
     oiseau
    -1.40
     необхідно
    -1.38
     -
    -1.37
     Although
    -1.35
     murky
    -1.35
     можли
    -1.34
    POSITIVE LOGITS
     the
    1.85
     {
    1.72
     they
    1.65
    ↵
    1.58
     genaue
    1.44
     czter
    1.41
     นิ้ว
    1.41
    vanced
    1.37
    цией
    1.31
     geburtstag
    1.30
    Activations Density 0.007%

    No Known Activations