© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41539
    Prev
    Next
    INDEX
    Explanations

    racial stereotypes and technology

    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
     αν
    0.44
     в
    0.42
    甚至
    0.42
    다면
    0.41
    ﻮ
    0.40
    ಂಚ
    0.40
     வ
    0.39
     કરવો
    0.39
    mining
    0.39
    வ
    0.39
    POSITIVE LOGITS
     parthen
    0.48
     sécher
    0.46
     それぞれ
    0.43
     regimens
    0.43
     punten
    0.43
     vignettes
    0.42
     intermitt
    0.41
     ដើម្បី
    0.41
     sutures
    0.40
     เพื่อ
    0.40
    Activations Density 0.016%

    No Known Activations