© 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. 10-GEMMASCOPE-RES-131K
    4. 3678
    Prev
    Next
    INDEX
    Explanations

    programming, data transformation, streams

    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_10/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
    所以我
    -1.63
    但在
    -1.60
    但也
    -1.57
    禤
    -1.56
    要不然
    -1.56
    但
    -1.56
    但是在
    -1.52
     we
    -1.51
    特别是
    -1.46
    们的
    -1.38
    POSITIVE LOGITS
    錞
    1.68
     uwag
    1.55
     fantástico
    1.53
    This
    1.48
    Église
    1.41
     населення
    1.38
    The
    1.38
     verlangen
    1.37
    corrhi
    1.37
    You
    1.34
    Activations Density 0.002%

    No Known Activations