© 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. 32375
    Prev
    Next
    INDEX
    Explanations

    stamp duty or taxes

    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
    mathsf
    -0.80
    dataGridView
    -0.72
     drivers
    -0.72
     travel
    -0.72
    atég
    -0.72
    สุข
    -0.71
    眺め
    -0.71
    瀧
    -0.71
    CBSE
    -0.70
    込めて
    -0.70
    POSITIVE LOGITS
     stamp
    1.38
    stamp
    1.26
    Stamp
    1.20
     STAMP
    1.20
     Stamp
    1.19
     Stam
    0.96
     stamps
    0.93
     transaction
    0.89
     Stamps
    0.88
    stam
    0.88
    Activations Density 0.003%

    No Known Activations