© 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. 36342
    Prev
    Next
    INDEX
    Explanations

    Latin words, names, and citations

    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
     at
    -2.30
     or
    -2.23
     and
    -2.17
     in
    -2.11
     for
    -2.09
     which
    -1.99
     if
    -1.95
     by
    -1.75
     as
    -1.73
     Excellent
    -1.63
    POSITIVE LOGITS
     extremely
    1.95
    訁
    1.91
     investimento
    1.89
     フラワー
    1.87
     amazingly
    1.87
     incredibly
    1.85
     gigantic
    1.83
     myriad
    1.82
     intriguing
    1.82
     continually
    1.82
    Activations Density 0.032%

    No Known Activations