© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2959
    Prev
    Next
    INDEX
    Explanations

    Startup, load, boot, or completion

    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
    burgo
    -0.87
    Alamat
    -0.85
     نقطه
    -0.81
    ENST
    -0.80
     erros
    -0.80
     विभिन्न
    -0.80
     épreuve
    -0.79
    nexo
    -0.79
    astrous
    -0.79
    ghế
    -0.78
    POSITIVE LOGITS
     arrival
    2.06
     startup
    1.75
     completion
    1.61
     creation
    1.57
     release
    1.45
     entry
    1.45
     entering
    1.43
     exit
    1.41
     receipt
    1.38
     launch
    1.34
    Activations Density 0.131%

    No Known Activations