© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106579
    Prev
    Next
    INDEX
    Explanations

    estate tax rates

    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
    michel
    -0.79
     shreds
    -0.78
     Burrows
    -0.77
     endometriosis
    -0.75
     wading
    -0.75
     invests
    -0.72
    ountain
    -0.71
    onnay
    -0.71
     acessórios
    -0.71
    füh
    -0.70
    POSITIVE LOGITS
     transfer
    1.23
     transfers
    1.20
    transfers
    1.15
     estate
    1.13
     Transfer
    1.05
    Transfers
    1.05
    transfer
    1.01
     Estate
    0.96
     Transfers
    0.95
    TRANSFER
    0.94
    Activations Density 0.008%

    No Known Activations