© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6223
    Prev
    Next
    INDEX
    Explanations

    progressive taxation policies

    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_40_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
    订
    0.53
    组织
    0.52
     Capabilities
    0.51
    细菌
    0.49
    导体
    0.49
     Machine
    0.49
    Machine
    0.48
     Processes
    0.48
     Microbiology
    0.48
    领导
    0.47
    POSITIVE LOGITS
     tax
    1.06
     taxes
    0.93
     reforms
    0.88
    稅
    0.84
     taxation
    0.82
    tax
    0.82
     taxe
    0.82
     taxed
    0.80
     reformers
    0.80
     levies
    0.78
    Activations Density 0.025%

    No Known Activations