© 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. 130759
    Prev
    Next
    INDEX
    Explanations

    what are they

    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
     krop
    -0.84
     '*')
    -0.81
    壊
    -0.79
    Pls
    -0.78
    ète
    -0.78
     kado
    -0.76
     Testamento
    -0.74
    ☻
    -0.74
     kül
    -0.74
     ویتامین
    -0.74
    POSITIVE LOGITS
     who
    1.23
     they
    1.16
    他們
    0.98
    他们
    0.96
    lussen
    0.93
    
    0.92
     mereka
    0.89
     они
    0.88
     ktorí
    0.88
     know
    0.87
    Activations Density 0.045%

    No Known Activations