© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 104156
    Prev
    Next
    INDEX
    Explanations

    protected characteristics discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ק
    1.09
    ب
    1.02
    ك
    0.97
    ী
    0.86
    ري
    0.84
    防
    0.80
    то
    0.78
    ти
    0.78
    し
    0.77
    ри
    0.77
    POSITIVE LOGITS
     protected
    1.20
     Protected
    1.03
     is
    0.82
    Protected
    0.82
     stort
    0.81
     CNS
    0.80
     was
    0.76
     session
    0.75
     photoshoot
    0.74
     dispenser
    0.73
    Activations Density 0.008%

    No Known Activations