© 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. 34-GEMMASCOPE-RES-131K
    7. 66217
    Prev
    Next
    INDEX
    Explanations

    object fields and types

    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
    Thesis
    -0.78
     Gastgeber
    -0.75
    返回值
    -0.72
     categoria
    -0.71
     Mike
    -0.71
    mators
    -0.70
    飢
    -0.69
     hereditary
    -0.69
    報道
    -0.68
     Cleary
    -0.68
    POSITIVE LOGITS
     table
    0.98
     Relocation
    0.93
    table
    0.90
    offset
    0.84
     phụ
    0.83
     offset
    0.83
    compressed
    0.82
     compressed
    0.79
     relocation
    0.79
     uzun
    0.79
    Activations Density 0.016%

    No Known Activations