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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70783
    Prev
    Next
    INDEX
    Explanations

    events completed or concluded

    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
    continued
    -0.94
     devenu
    -0.94
     devenue
    -0.90
    now
    -0.90
     домашних
    -0.89
    isler
    -0.88
     comprennent
    -0.87
     xxiv
    -0.85
    ersonal
    -0.84
    fif
    -0.84
    POSITIVE LOGITS
     successful
    1.45
     completed
    1.25
     successfully
    1.24
     success
    1.23
     after
    1.23
     results
    1.20
     ended
    1.16
     finished
    1.16
     result
    1.14
    の結果
    1.12
    Activations Density 0.127%

    No Known Activations