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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32928
    Prev
    Next
    INDEX
    Explanations

    action of contract

    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
    花の
    -0.85
     länge
    -0.81
     inmigrantes
    -0.81
     museos
    -0.76
    hibitions
    -0.74
     Noi
    -0.73
    倜
    -0.73
    Consts
    -0.72
     allows
    -0.71
    è
    -0.71
    POSITIVE LOGITS
     contract
    1.63
    Contract
    1.60
     Contract
    1.56
    contract
    1.50
     contractual
    1.37
     CONTRACT
    1.20
     tort
    1.18
     negligence
    1.08
     Contracts
    1.03
     kontrak
    0.97
    Activations Density 0.033%

    No Known Activations