© 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. 93481
    Prev
    Next
    INDEX
    Explanations

    academia industry government

    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
     or
    -0.91
    ogical
    -0.87
    Cafe
    -0.87
    ſ
    -0.87
    cripciones
    -0.83
    вге
    -0.83
    プライズ
    -0.83
    asted
    -0.83
    WidgetItem
    -0.82
    Handlers
    -0.82
    POSITIVE LOGITS
     academia
    2.28
     academic
    2.11
     government
    2.02
     industry
    1.91
     academics
    1.85
    academia
    1.77
    academic
    1.57
     university
    1.45
     governmental
    1.45
    government
    1.38
    Activations Density 0.059%

    No Known Activations