© 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. 22-GEMMASCOPE-RES-131K
    7. 33208
    Prev
    Next
    INDEX
    Explanations

    hotels, prices, Pancreatic, Residence, As distracted, Q

    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_22/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
     Japão
    -1.11
     their
    -1.04
     løpet
    -0.98
    akteur
    -0.98
     ilha
    -0.93
     escritório
    -0.92
    què
    -0.90
     only
    -0.90
     døde
    -0.90
     last
    -0.89
    POSITIVE LOGITS
     lựa
    1.04
    ضی
    1.02
     곳
    0.98
    alahkan
    0.98
     pilihan
    0.96
    เลือก
    0.94
     کیلوم
    0.94
    껍
    0.91
     anlam
    0.91
    Cerca
    0.90
    Activations Density 0.002%

    No Known Activations