© 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. 49714
    Prev
    Next
    INDEX
    Explanations

    claims of priority and applications

    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
     observed
    -0.72
     find
    -0.68
     mengan
    -0.67
     Trieb
    -0.67
    Rp
    -0.67
    wann
    -0.67
    tening
    -0.66
    endet
    -0.66
    Durata
    -0.66
     despe
    -0.65
    POSITIVE LOGITS
     priority
    1.17
    priority
    1.11
     applications
    1.09
    CIP
    1.07
    applications
    1.02
     Priority
    0.94
    Priority
    0.93
    Applications
    0.91
     application
    0.90
     Application
    0.90
    Activations Density 0.386%

    No Known Activations