© 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. 3766
    Prev
    Next
    INDEX
    Explanations

    income statistics households Hispanic

    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
    架构
    0.61
    鲷
    0.61
    传说
    0.59
    绛
    0.59
    展现
    0.58
    触发
    0.58
    Methylsulfanyl
    0.58
    懑
    0.58
    舰队
    0.57
     ilgi
    0.57
    POSITIVE LOGITS
     households
    0.69
     household
    0.68
    household
    0.63
    adjusted
    0.59
     Hispanic
    0.57
    業
    0.57
     Households
    0.56
     Americans
    0.54
    median
    0.54
     Hispanics
    0.54
    Activations Density 0.090%

    No Known Activations