© 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. 71466
    Prev
    Next
    INDEX
    Explanations

    also available

    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
     both
    -1.63
     only
    -1.21
     everything
    -1.14
     therefore
    -1.09
     first
    -1.08
     began
    -1.07
     facilitating
    -1.06
     this
    -1.04
    勛
    -1.03
     one
    -1.02
    POSITIVE LOGITS
    "):
    
    1.07
     grupper
    1.05
     verticale
    1.04
    :</
    1.02
    OrBuilder
    1.01
    ,
    1.00
    sa
    0.99
     geniales
    0.99
    k
    0.98
    ():
    
    0.97
    Activations Density 0.012%

    No Known Activations