© 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. 25402
    Prev
    Next
    INDEX
    Explanations

    ethnic and geographic groups

    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
     behem
    0.52
    television
    0.40
    V
    0.40
     inconvenience
    0.40
    M
    0.39
    モス
    0.38
     campaigner
    0.38
    URLException
    0.38
    |>
    0.37
     of
    0.37
    POSITIVE LOGITS
     Clustering
    0.48
    旪
    0.47
    秚
    0.47
    orthin
    0.43
    🎣
    0.43
    秥
    0.42
    旕
    0.42
     siguiendo
    0.42
     Ensuring
    0.42
     Boundaries
    0.41
    Activations Density 0.001%

    No Known Activations