© 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. 93175
    Prev
    Next
    INDEX
    Explanations

    why or when something happens

    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
     ENGINEERS
    -1.06
     dreary
    -1.05
     certamente
    -1.03
     verurs
    -0.98
    และ
    -0.97
    efit
    -0.96
    
    -0.96
    liana
    -0.95
     NORTHERN
    -0.94
    ţele
    -0.93
    POSITIVE LOGITS
     people
    1.09
     because
    1.09
    After
    1.07
    Very
    1.05
     after
    1.03
    Despite
    1.02
     at
    1.01
     unparalleled
    0.99
    Often
    0.98
    Because
    0.97
    Activations Density 0.147%

    No Known Activations