© 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. 34-GEMMASCOPE-RES-131K
    7. 2111
    Prev
    Next
    INDEX
    Explanations

    assertions and checks

    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_34/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
     почему
    -0.83
     Почему
    -0.81
     nursed
    -0.80
    adaan
    -0.80
    Fiz
    -0.80
     Why
    -0.77
    
    -0.76
    蒻
    -0.76
     Conqueror
    -0.75
    Lepid
    -0.75
    POSITIVE LOGITS
     argue
    1.07
     assert
    1.02
     asserts
    1.02
     afirma
    0.98
     argument
    0.95
    either
    0.94
    assert
    0.92
     Argument
    0.90
     '',
    0.89
     sorpresas
    0.89
    Activations Density 0.012%

    No Known Activations