© 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. 73930
    Prev
    Next
    INDEX
    Explanations

    coordinates and units

    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
     With
    -1.73
    With
    -1.65
     provide
    -1.57
    After
    -1.54
     typically
    -1.52
     usually
    -1.52
     give
    -1.50
     Usually
    -1.50
     enables
    -1.48
    Before
    -1.47
    POSITIVE LOGITS
     dando
    1.62
    🫅
    1.59
    <bos>
    1.59
    但这
    1.56
     soooo
    1.55
     evocative
    1.49
    を使用
    1.45
    臜
    1.45
     contando
    1.42
     sooo
    1.41
    Activations Density 0.001%

    No Known Activations