© 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. 10-GEMMASCOPE-RES-131K
    7. 101054
    Prev
    Next
    INDEX
    Explanations

    block and transaction queries

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

    words related to blockchain, cryptocurrency transactions, and technical data structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    fani
    -1.62
    f
    -1.52
    o
    -1.43
     soprattutto
    -1.41
    zione
    -1.38
    in
    -1.34
     ナイロン
    -1.33
     dessas
    -1.32
    </h1>
    -1.30
    ции
    -1.30
    POSITIVE LOGITS
    Tento
    1.64
     impossível
    1.64
     hacían
    1.48
    iç
    1.45
    Aktual
    1.45
    masuk
    1.43
     hacerte
    1.41
    низ
    1.41
    unser
    1.40
    mohon
    1.40
    Activations Density 0.005%

    No Known Activations