© 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. 27088
    Prev
    Next
    INDEX
    Explanations

    updates and progress

    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
     venerable
    -1.10
     MUCH
    -1.06
    /
    -1.05
     заметил
    -1.03
    lète
    -1.02
     неда
    -1.00
    PLAUSE
    -0.99
     khung
    -0.97
    "
    -0.97
     yapmak
    -0.97
    POSITIVE LOGITS
     updates
    2.16
    进展
    1.90
     progress
    1.72
     update
    1.60
     perkembangan
    1.57
     status
    1.50
    status
    1.46
    progress
    1.45
     developments
    1.44
     progrès
    1.44
    Activations Density 0.030%

    No Known Activations