© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38958
    Prev
    Next
    INDEX
    Explanations

    3D scene, shapes, model, graphics

    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
     juiz
    -2.02
     indiví
    -1.98
     veículo
    -1.84
     Unglück
    -1.81
     допо
    -1.80
     caminhão
    -1.80
    
    -1.77
    垍
    -1.73
    画家
    -1.72
     Können
    -1.70
    POSITIVE LOGITS
    鱨
    1.58
     is
    1.57
     impede
    1.57
    几种
    1.46
     svým
    1.45
     dlouho
    1.42
    C
    1.42
     ‘
    1.35
     contribute
    1.34
    izing
    1.32
    Activations Density 0.021%

    No Known Activations