© 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. 116415
    Prev
    Next
    INDEX
    Explanations

    ejection or banishment

    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
     armazen
    -0.75
     βα
    -0.73
     Linder
    -0.73
    寅
    -0.73
     situações
    -0.71
     personalizar
    -0.71
    decode
    -0.71
    neid
    -0.70
     kèo
    -0.70
    críbete
    -0.69
    POSITIVE LOGITS
     expulsion
    3.88
     expelled
    3.61
     expel
    3.13
     expuls
    3.13
     ejection
    2.97
     ejected
    2.81
     eject
    2.80
     eviction
    2.77
     evicted
    2.50
     booted
    2.27
    Activations Density 0.089%

    No Known Activations