© 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. 98489
    Prev
    Next
    INDEX
    Explanations

    numbers followed by letters or punctuation

    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
    ↵
    -0.93
     متح
    -0.93
     нескольких
    -0.90
    倒
    -0.90
    even
    -0.86
    诟
    -0.85
    としている
    -0.85
     needed
    -0.84
     نداشت
    -0.84
    self
    -0.83
    POSITIVE LOGITS
     afternoon
    1.45
     великолеп
    1.33
     evening
    1.12
    тій
    1.08
    ząt
    1.07
    
    1.05
    इटम
    1.04
    ꪔ
    1.02
    溷
    0.99
    zdě
    0.98
    Activations Density 0.006%

    No Known Activations