© 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. 136676
    Prev
    Next
    INDEX
    Explanations

    harmful stereotypes and sexual objectification

    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
    CURRENT
    0.52
     이론
    0.51
    kjhtml
    0.48
    thorax
    0.46
    PROTE
    0.45
     બ
    0.45
    падает
    0.44
    mesinin
    0.44
    PACS
    0.44
     軍
    0.44
    POSITIVE LOGITS
     utter
    0.42
     bewe
    0.42
     mener
    0.41
    ט
    0.41
    جاه
    0.41
     podataka
    0.41
     things
    0.41
    ധി
    0.41
     tradu
    0.40
     attractions
    0.40
    Activations Density 0.006%

    No Known Activations