© 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. 12612
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    .“
    -2.39
    and
    -2.38
     ulteriori
    -2.33
     tetapi
    -2.23
    ”.
    -2.23
     namun
    -2.19
    ânica
    -2.17
    {
    -2.16
    but
    -2.16
    。“
    -2.11
    POSITIVE LOGITS
     "
    3.72
     ''
    3.00
     '
    2.92
     
    2.63
     "...
    2.55
     espíritu
    2.55
    ?"
    2.52
    蓠
    2.34
     spooky
    2.33
     berätt
    2.28
    Activations Density 0.002%

    No Known Activations