© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78952
    Prev
    Next
    INDEX
    Explanations

    political parties and nations

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

    The neuron strongly activates on references to left‐wing political groups, ideologies, and figures (e.g. labour, Marxists, Karl, Rosa Luxembourg).

    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
    wachung
    -0.77
    orienti
    -0.75
     Ito
    -0.74
    цкая
    -0.73
    lant
    -0.71
    宣传
    -0.71
    är
    -0.70
     Soros
    -0.69
     chew
    -0.69
     המח
    -0.69
    POSITIVE LOGITS
     Trotsky
    1.55
     Leon
    1.03
    Leon
    0.98
    defence
    0.78
     Entrada
    0.77
     Deutscher
    0.77
     LEON
    0.76
     Milit
    0.75
     Permanent
    0.73
     Merv
    0.72
    Activations Density 0.021%

    No Known Activations