© 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. 22-GEMMASCOPE-RES-131K
    7. 71467
    Prev
    Next
    INDEX
    Explanations

    anniversary or birthday celebrations

    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
     smtplib
    -1.28
    もありますが
    -1.15
     nyní
    -1.15
    もあって
    -1.11
     discours
    -1.10
     teraz
    -1.09
     Pilipinas
    -1.07
     portions
    -1.06
     now
    -1.05
     jusqu
    -1.05
    POSITIVE LOGITS
     anniversary
    1.37
     birthday
    1.28
    Fakta
    1.15
     birthdays
    1.12
     important
    1.10
     their
    1.10
    uluş
    1.10
     celebration
    1.09
    ();*/
    1.09
    versary
    1.06
    Activations Density 0.019%

    No Known Activations