© 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. 32146
    Prev
    Next
    INDEX
    Explanations

    trustee paying

    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
     рот
    -0.84
    ----|
    -0.82
    TOBER
    -0.80
    nergy
    -0.80
    KYO
    -0.78
    DEPARTMENT
    -0.77
     EMPLOYEE
    -0.77
     Applicant
    -0.76
    cookieParser
    -0.75
     iub
    -0.74
    POSITIVE LOGITS
     trustee
    1.01
     paying
    0.89
     Trustee
    0.85
     especiales
    0.78
    paying
    0.75
     trustees
    0.74
    Paying
    0.73
     Paying
    0.71
     bruised
    0.71
     agent
    0.69
    Activations Density 0.014%

    No Known Activations