© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39989
    Prev
    Next
    INDEX
    Explanations

    surname or personal name

    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
     direkten
    -0.98
    搭載
    -0.95
     hóspedes
    -0.87
     explicado
    -0.85
     בשנת
    -0.85
    ホームページ
    -0.84
    StringBuffer
    -0.82
    จาก
    -0.82
    купить
    -0.82
     experimentado
    -0.81
    POSITIVE LOGITS
     family
    1.43
     esfuer
    0.98
    family
    0.96
     interesan
    0.89
    nicy
    0.86
     oar
    0.84
    aconda
    0.84
    کتور
    0.84
    çamento
    0.84
     Family
    0.84
    Activations Density 0.019%

    No Known Activations