© 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. 28060
    Prev
    Next
    INDEX
    Explanations

    thanks, please, recently

    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
     deinen
    -1.12
     then
    -1.10
     ใช้
    -1.05
     delà
    -0.98
    igers
    -0.96
    ご連絡
    -0.96
    gén
    -0.95
    けどね
    -0.94
    riebene
    -0.94
     toppen
    -0.94
    POSITIVE LOGITS
     this
    1.02
     asking
    1.00
     I
    0.96
    🅗
    0.95
     longstanding
    0.94
     Please
    0.91
    ábbi
    0.90
     recently
    0.90
    During
    0.89
     showcasing
    0.89
    Activations Density 0.025%

    No Known Activations