© 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. 32598
    Prev
    Next
    INDEX
    Explanations

    tax, revenue, relief, penalty, return, cancer, commissioners

    np_acts-logits-general · gemini-2.5-flash-lite

    government or tax-related documents and information.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     دولة
    -0.78
    ختی
    -0.74
     photosynthetic
    -0.73
     violations
    -0.71
     STYLES
    -0.70
     Ascot
    -0.69
    wollen
    -0.68
    нор
    -0.68
     violates
    -0.68
     invoices
    -0.67
    POSITIVE LOGITS
    ffron
    0.75
    gangenheit
    0.73
    })),
    0.73
    iker
    0.71
     fang
    0.71
     préfé
    0.71
    書店
    0.71
    Coff
    0.70
     carcinoma
    0.69
    relser
    0.69
    Activations Density 0.016%

    No Known Activations