© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50789
    Prev
    Next
    INDEX
    Explanations

    slaveslaveryenslaved people

    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
    стая
    0.46
    隈
    0.43
    目录
    0.43
    पीठ
    0.43
    釣
    0.42
    तिर
    0.42
    டனும்
    0.41
    🌉
    0.41
    एं
    0.41
    entliche
    0.41
    POSITIVE LOGITS
     slave
    1.10
     slavery
    1.09
     slaves
    0.98
    slave
    0.98
     esclav
    0.98
     enslaved
    0.98
     Slavery
    0.96
     Slave
    0.93
     ensl
    0.92
    Slave
    0.90
    Activations Density 0.055%

    No Known Activations