© 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. 22-GEMMASCOPE-RES-131K
    4. 9324
    Prev
    Next
    INDEX
    Explanations

    delimiters in lists

    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
     zoude
    -2.34
     TÉ
    -2.22
    ఝ
    -2.17
     italiens
    -2.16
     pérd
    -2.14
     corriger
    -2.09
     maniere
    -2.09
     estadounid
    -2.09
     própri
    -2.08
     alho
    -2.08
    POSITIVE LOGITS
     to
    2.31
     all
    2.17
     for
    2.17
     and
    2.13
     in
    2.11
     including
    2.05
     as
    2.05
     still
    2.03
     What
    2.02
     even
    1.91
    Activations Density 0.013%

    No Known Activations