© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22920
    Prev
    Next
    INDEX
    Explanations

    male/female concepts

    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_31_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
    وع
    0.55
    س
    0.53
    ر
    0.50
    ла
    0.49
    اس
    0.47
    سر
    0.47
    ти
    0.47
    𝒌
    0.46
    स्की
    0.46
    kve
    0.46
    POSITIVE LOGITS
    0.48
     provoked
    0.46
     गोष्ट
    0.42
    "},{"
    0.42
     reception
    0.41
    }{
    0.40
     pastime
    0.40
     brewed
    0.39
     monoclonal
    0.39
     hemispheres
    0.39
    Activations Density 0.002%

    No Known Activations