© 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. 10-GEMMASCOPE-RES-131K
    7. 123862
    Prev
    Next
    INDEX
    Explanations

    news dateline words

    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
    When
    -2.81
    If
    -2.72
    N
    -2.58
    Just
    -2.47
    Even
    -2.45
    姈
    -2.42
     invigor
    -2.42
    To
    -2.38
    Sometimes
    -2.38
    You
    -2.36
    POSITIVE LOGITS
    寕
    2.67
     "
    2.66
    งิน
    2.64
    鉿
    2.61
    enablog
    2.56
    Odpovědět
    2.48
    はこの
    2.48
     was
    2.47
    makeat
    2.45
    厛
    2.36
    Activations Density 0.042%

    No Known Activations