© 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-262K
    7. 125724
    Prev
    Next
    INDEX
    Explanations

    negative social constructs

    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
     K
    0.54
     Se
    0.50
     S
    0.50
     ప్రతి
    0.50
     К
    0.50
    р
    0.49
     Архивная
    0.48
     R
    0.47
     alumn
    0.46
     ’
    0.46
    POSITIVE LOGITS
    צא
    0.42
    curr
    0.39
    oja
    0.38
    בות
    0.38
    ляется
    0.38
    这些人
    0.38
    이면
    0.37
    izaje
    0.37
     ພວກເຮົາ
    0.37
    zę
    0.37
    Activations Density 0.003%

    No Known Activations