© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6847
    Prev
    Next
    INDEX
    Explanations

    secession and independence movements

    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
    悴
    -0.82
     Managua
    -0.81
     nasi
    -0.81
    못
    -0.79
     三角
    -0.78
    ntgen
    -0.75
    ATUR
    -0.75
    Constraints
    -0.75
     lata
    -0.74
     Croce
    -0.74
    POSITIVE LOGITS
     separ
    2.81
     secession
    2.36
     Separ
    2.17
     separation
    2.09
     independence
    2.05
    separ
    2.03
     Separation
    1.95
    Separ
    1.88
    separation
    1.77
     separación
    1.77
    Activations Density 0.040%

    No Known Activations