© 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. 60179
    Prev
    Next
    INDEX
    Explanations

    Liberal political discourse

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

    This neuron responds to tokens that are proper-name or numeric entities—i.e. capitalized names (esp. politicians/parties) and standalone numbers/digits.

    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
     Bres
    -0.75
     Hamas
    -0.73
    Marx
    -0.73
     入り
    -0.71
    ☭
    -0.71
    拈
    -0.68
    ]==
    -0.68
     kli
    -0.68
    dron
    -0.68
    Freight
    -0.68
    POSITIVE LOGITS
     Liberal
    1.76
    Liberal
    1.51
     liberal
    1.44
     liberalism
    1.41
    liberal
    1.32
     FDP
    1.22
     liberals
    1.20
     Lib
    1.15
     Liberals
    1.04
     libéral
    1.03
    Activations Density 0.041%

    No Known Activations