© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40058
    Prev
    Next
    INDEX
    Explanations

    discrimination and favoritism

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

    bias and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ग्रेड
    0.48
     caliente
    0.44
     konstant
    0.44
    kontrol
    0.43
    ⢸
    0.41
     nodo
    0.41
     juguete
    0.41
     consequat
    0.40
     கட்டுமானம்
    0.40
    ologio
    0.40
    POSITIVE LOGITS
     выборах
    0.46
     discussions
    0.46
     by
    0.43
     ವರ್
    0.43
    дания
    0.42
    шымта
    0.41
     ballots
    0.41
    ৩২
    0.41
     Alberta
    0.40
     話
    0.40
    Activations Density 0.000%

    No Known Activations