© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107423
    Prev
    Next
    INDEX
    Explanations

    fiscal year, fiscal cliff

    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
    δρο
    -0.91
     défini
    -0.91
     obno
    -0.90
     Atención
    -0.89
     dusky
    -0.88
    Lokal
    -0.88
     Prevents
    -0.88
    Titulo
    -0.88
    ejemplo
    -0.88
    NEVER
    -0.86
    POSITIVE LOGITS
     year
    1.01
     fiscal
    0.93
     Fiscal
    0.85
     cliff
    0.83
    ized
    0.82
     год
    0.81
    参考
    0.79
    Fiscal
    0.79
     Responsibility
    0.79
     die
    0.78
    Activations Density 0.003%

    No Known Activations