© 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. 108565
    Prev
    Next
    INDEX
    Explanations

    developing countries, fragile states

    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
    urat
    -0.80
    💃
    -0.77
    lamation
    -0.72
    Matériel
    -0.72
    сіб
    -0.71
    Scher
    -0.71
     Mexican
    -0.70
     grpc
    -0.68
     vapormax
    -0.68
     Mexico
    -0.67
    POSITIVE LOGITS
     Least
    1.40
     poorest
    1.36
    Least
    1.32
     least
    1.21
    least
    1.11
     fragile
    0.88
    Nepal
    0.84
    женные
    0.84
    IDA
    0.83
     LL
    0.82
    Activations Density 0.021%

    No Known Activations