© 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. 75218
    Prev
    Next
    INDEX
    Explanations

    Commercial fields

    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
     arbejde
    -0.98
    샀
    -0.93
    طاق
    -0.90
    entuk
    -0.90
     even
    -0.88
    』(
    -0.86
    crites
    -0.85
    cją
    -0.85
     चाहिए
    -0.85
    ولة
    -0.84
    POSITIVE LOGITS
     wonderfully
    1.01
     cervello
    0.98
     hivyo
    0.98
    Thus
    0.96
     astonishing
    0.95
    ={()=>
    0.94
     wonderful
    0.94
    thus
    0.93
     Selecciona
    0.93
     Franse
    0.93
    Activations Density 0.007%

    No Known Activations