© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21611
    Prev
    Next
    INDEX
    Explanations

    accounting and accounts

    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_all/layer_41_width_262k_l0_big
    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
    eiros
    0.39
     લાવ
    0.36
    ፈላጊ
    0.36
    ામ
    0.34
    examples
    0.34
     +"\
    0.34
    मित्व
    0.33
     shay
    0.33
    [multimodal]
    0.33
     造
    0.33
    POSITIVE LOGITS
     accounting
    2.02
     accounted
    1.87
     учиты
    1.87
     account
    1.79
     factoring
    1.77
     Accounting
    1.73
    accounting
    1.73
    Accounting
    1.72
     rekening
    1.64
     учета
    1.63
    Activations Density 0.003%

    No Known Activations