© 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. 31-GEMMASCOPE-2-RES-65K
    7. 41044
    Prev
    Next
    INDEX
    Explanations

    harmful stereotypes exploitation

    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_65k_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
    नाची
    0.46
    zon
    0.45
    เหตุ
    0.45
    zei
    0.45
    drá
    0.44
    噬
    0.44
     unanim
    0.44
    politik
    0.44
    lias
    0.43
    isem
    0.43
    POSITIVE LOGITS
     Extend
    0.47
     Commencez
    0.46
     حلق
    0.46
    ؟
    0.45
     كم
    0.45
     Execute
    0.44
    ،
    0.44
    ுகிறார்கள்
    0.43
     واست
    0.43
     Comfortable
    0.43
    Activations Density 0.030%

    No Known Activations