© 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. 110505
    Prev
    Next
    INDEX
    Explanations

    AS followed by numbers or acronyms

    np_acts-logits-general · gemini-2.5-flash-lite

    the character sequence "AS" followed by a digit, typically representing acronyms, abbreviations, or version numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ꦢ
    -3.02
    ：（
    -2.52
    柃
    -2.50
     }}$}
    -2.48
    寕
    -2.47
     peruano
    -2.45
    ꠥ
    -2.39
    ))$_
    -2.36
    ꪔ
    -2.36
    是我们
    -2.33
    POSITIVE LOGITS
    _
    2.88
     `
    2.83
     {
    2.69
     AS
    2.64
    也许
    2.48
     impromptu
    2.41
     famed
    2.36
     picturesque
    2.27
     Häufig
    2.27
     Then
    2.25
    Activations Density 0.011%

    No Known Activations