© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65215
    Prev
    Next
    INDEX
    Explanations

    cooking the books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tetanus
    -0.75
    Carte
    -0.74
     vlož
    -0.71
    ższe
    -0.70
    頭髮
    -0.68
    Preparazione
    -0.68
     Coleridge
    -0.68
     Habe
    -0.67
     prevista
    -0.66
    ଉ
    -0.66
    POSITIVE LOGITS
     accounting
    3.05
    accounting
    2.52
     Accounting
    2.47
     bookkeeping
    2.41
    Accounting
    2.33
     бухгал
    1.80
     accountants
    1.73
     accountant
    1.73
     double
    1.72
    double
    1.67
    Activations Density 0.019%

    No Known Activations