© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4407
    Prev
    Next
    INDEX
    Explanations

    Oh interjections

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

    Oh and wow expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Consulting
    0.39
     Consultant
    0.39
     Freizeit
    0.38
     incul
    0.36
     অধ
    0.35
     paras
    0.35
    払
    0.35
    reta
    0.34
    PIRED
    0.34
     Consultants
    0.34
    POSITIVE LOGITS
     wow
    3.28
     Wow
    3.05
     WOW
    3.05
    wow
    2.88
    WOW
    2.84
    Wow
    2.83
     OMG
    1.90
    哇
    1.82
     omg
    1.75
     damn
    1.67
    Activations Density 0.208%

    No Known Activations