© 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. 49529
    Prev
    Next
    INDEX
    Explanations

    type or subtype clarification

    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
     Closet
    -0.82
     backyard
    -0.81
    Storage
    -0.80
    
    -0.79
    Matchers
    -0.78
    Animation
    -0.78
     Staging
    -0.77
    踅
    -0.77
     legged
    -0.76
     sierp
    -0.75
    POSITIVE LOGITS
     дис
    0.93
     自动
    0.91
     dispenser
    0.91
     Dispens
    0.90
    自动
    0.86
     dispens
    0.85
     dispense
    0.85
    自動
    0.85
     push
    0.84
     vandal
    0.84
    Activations Density 0.017%

    No Known Activations