© 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. 54692
    Prev
    Next
    INDEX
    Explanations

    tax deductibility

    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
    打开
    0.44
    第
    0.43
    What
    0.42
     collegamento
    0.42
    打開
    0.42
    亮
    0.41
     What
    0.41
    [
    0.41
     打开
    0.40
     Anyone
    0.39
    POSITIVE LOGITS
    投资基金
    0.50
     persec
    0.49
     exuber
    0.46
     foment
    0.45
     lepid
    0.45
     ਕਰ
    0.44
     materialistic
    0.44
     NFS
    0.43
     aristocracy
    0.43
    蛜
    0.43
    Activations Density 0.003%

    No Known Activations