© 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. 22-GEMMASCOPE-RES-131K
    7. 95673
    Prev
    Next
    INDEX
    Explanations

    West Ham

    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
    ଶ
    -0.87
     didn
    -0.85
     each
    -0.85
    リゾート
    -0.84
    每一个
    -0.84
    摂取
    -0.84
     الشاشة
    -0.83
     penonton
    -0.83
     more
    -0.81
    五六
    -0.77
    POSITIVE LOGITS
    Surgical
    1.01
    ᐛ
    0.98
    哢
    0.92
    Ingestion
    0.90
    inę
    0.90
     pell
    0.89
     کردیم
    0.87
    ilogue
    0.87
    EVALUATION
    0.87
     quente
    0.86
    Activations Density 0.001%

    No Known Activations