© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118644
    Prev
    Next
    INDEX
    Explanations

    contracts and agreements

    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
     Signing
    -1.20
    Signing
    -1.13
     signing
    -1.06
    签
    -0.94
     signatory
    -0.87
     đàn
    -0.85
    ובת
    -0.82
     signings
    -0.81
     Vertrags
    -0.80
     firmar
    -0.80
    POSITIVE LOGITS
     agreement
    1.40
     agreements
    1.31
     with
    1.05
     contracts
    1.01
     employment
    0.97
     Agreement
    0.96
     Master
    0.93
     master
    0.93
     sales
    0.93
     loan
    0.92
    Activations Density 0.096%

    No Known Activations