© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11428
    Prev
    Next
    INDEX
    Explanations

    code annotations and attributes

    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
     cuối
    -1.13
     estrela
    -0.91
     grossesse
    -0.90
    อื่น
    -0.89
    最后一个
    -0.86
    最后
    -0.85
    ingi
    -0.84
     autorité
    -0.82
    enderal
    -0.82
    Решение
    -0.82
    POSITIVE LOGITS
     мест
    0.89
     TextEditing
    0.86
     mentre
    0.84
    ram
    0.82
    anego
    0.80
     Robots
    0.79
     einzu
    0.79
     人民
    0.79
     largely
    0.78
    reditation
    0.78
    Activations Density 0.005%

    No Known Activations