© 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. 34-GEMMASCOPE-RES-131K
    7. 32738
    Prev
    Next
    INDEX
    Explanations

    completing prepositional phrases

    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
     colonies
    -0.95
     colony
    -0.82
    
    -0.81
    راع
    -0.80
    colony
    -0.77
    Externé
    -0.75
     AtomicInteger
    -0.74
    ostomy
    -0.74
    ssent
    -0.74
     Remastered
    -0.72
    POSITIVE LOGITS
     ICD
    0.75
     Discord
    0.72
    ADOR
    0.70
    くださいませ
    0.70
     redox
    0.69
    झ
    0.68
     grotte
    0.68
     NSA
    0.68
    責任
    0.68
     HUD
    0.67
    Activations Density 0.024%

    No Known Activations