© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48421
    Prev
    Next
    INDEX
    Explanations

    insurance, Mexico, financial entities

    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
    快乐
    -0.90
    րան
    -0.84
     äuß
    -0.83
     abroad
    -0.82
     Speisen
    -0.81
    لبة
    -0.81
    fora
    -0.80
    colta
    -0.80
     różnych
    -0.79
    えている
    -0.79
    POSITIVE LOGITS
     Derfor
    0.87
     insurer
    0.86
     Mexico
    0.84
     страхо
    0.83
     todays
    0.83
    ยนต์
    0.81
     канал
    0.79
    otesi
    0.77
     fled
    0.77
    𝔳
    0.77
    Activations Density 0.001%

    No Known Activations