© 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. 22-GEMMASCOPE-RES-131K
    7. 79940
    Prev
    Next
    INDEX
    Explanations

    biased or partisan

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

    The neuron fires on language that signals external influence, bias, or corrupting financial/political motives (e.g. “influenced by the financial interests,” “corrupt nature,” “paid,” “marketing,” “biased”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    itars
    -0.99
    ]$,
    -0.91
     изменя
    -0.91
    羨
    -0.91
    lowns
    -0.88
    วา
    -0.88
     odleg
    -0.84
    ņas
    -0.84
     графи
    -0.83
     alcune
    -0.83
    POSITIVE LOGITS
     biased
    1.42
     bias
    1.20
    bias
    1.16
    biased
    1.14
     partisan
    1.06
    Bias
    0.97
     Trouver
    0.91
    偏
    0.88
    hos
    0.88
     biases
    0.87
    Activations Density 0.037%

    No Known Activations