© 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. 31718
    Prev
    Next
    INDEX
    Explanations

    amortization and financial terms

    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
     اکاؤن
    0.63
     Accountants
    0.59
    万美元
    0.59
    壹章
    0.59
     бухгал
    0.59
     Accountant
    0.59
    肐
    0.59
    帳に追加
    0.58
    会计
    0.56
     매출
    0.56
    POSITIVE LOGITS
     transfer
    0.52
     held
    0.51
    vas
    0.51
     gain
    0.51
    if
    0.49
     \
    0.49
    sequ
    0.48
     embedded
    0.48
     fair
    0.47
    0.47
    Activations Density 0.011%

    No Known Activations