© 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. 38085
    Prev
    Next
    INDEX
    Explanations

    annual financial calculations

    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
     먹
    -0.96
    vocations
    -0.94
     commande
    -0.92
    feeling
    -0.85
    +<
    -0.85
    vidos
    -0.84
    صیلات
    -0.84
    improve
    -0.83
     OUR
    -0.82
    improving
    -0.82
    POSITIVE LOGITS
     California
    0.94
    年的
    0.91
     firms
    0.88
     annual
    0.88
     Year
    0.87
    Computation
    0.85
    Exhibit
    0.84
    溢
    0.81
     Solver
    0.81
     years
    0.80
    Activations Density 0.005%

    No Known Activations