© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5400
    Prev
    Next
    INDEX
    Explanations

    gender and sexual orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
    ter
    1.77
    are
    1.65
    or
    1.58
    ة
    1.52
    ere
    1.48
    ip
    1.48
    helps
    1.46
    hen
    1.45
    w
    1.43
    ry
    1.42
    POSITIVE LOGITS
    कर्मियों
    1.58
    یل
    1.54
     fomentar
    1.49
    ्स
    1.48
    től
    1.45
    문제
    1.45
    ಕ
    1.45
    preneur
    1.43
    بور
    1.43
    
    1.43
    Activations Density 0.127%

    No Known Activations