© 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. 22-GEMMASCOPE-RES-131K
    7. 128044
    Prev
    Next
    INDEX
    Explanations

    disclosure of bias and motives

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    瘠
    -0.86
     ideia
    -0.84
     Cout
    -0.80
     مجتمع
    -0.79
    EMPO
    -0.79
    щет
    -0.78
    barkeit
    -0.77
    tslib
    -0.77
    Quelles
    -0.77
    لائ
    -0.77
    POSITIVE LOGITS
     bias
    1.35
     objectivity
    1.18
     disclosure
    1.05
    рано
    1.02
    bias
    1.02
     impartiality
    1.01
     dévo
    0.96
     biases
    0.96
     disclose
    0.94
    Bias
    0.93
    Activations Density 0.073%

    No Known Activations