© 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. 20451
    Prev
    Next
    INDEX
    Explanations

    code closing brackets and parentheses

    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
    If
    -2.94
    8
    -2.83
     The
    -2.59
    a
    -2.47
    или
    -2.42
    6
    -2.28
     &
    -2.23
    3
    -2.22
    It
    -2.19
    _{
    -2.17
    POSITIVE LOGITS
    durante
    2.72
    灩
    2.67
    ientos
    2.52
    ⢪
    2.38
     malé
    2.36
    肜
    2.27
    瘜
    2.25
    瓩
    2.25
     vistos
    2.23
     contín
    2.19
    Activations Density 0.003%

    No Known Activations